diff --git a/docs/zh_CN/tutorials/getting_started.md b/docs/zh_CN/tutorials/getting_started.md
index 5a3ede676..7356e2c1a 100644
--- a/docs/zh_CN/tutorials/getting_started.md
+++ b/docs/zh_CN/tutorials/getting_started.md
@@ -22,13 +22,13 @@ PaddleClas目前支持的训练/评估环境如下：
准备好配置文件之后，可以使用下面的方式启动训练。
```
-python tools/train.py \
- -c configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
- -o pretrained_model="" \
- -o use_gpu=True
+python3 tools/train.py \
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml \
+ -o Arch.pretrained=False \
+ -o Global.device=gpu
```
-其中，`-c`用于指定配置文件的路径，`-o`用于指定需要修改或者添加的参数，其中`-o pretrained_model=""`表示不使用预训练模型，`-o use_gpu=True`表示使用GPU进行训练。如果希望使用CPU进行训练，则需要将`use_gpu`设置为`False`。
+其中，`-c`用于指定配置文件的路径，`-o`用于指定需要修改或者添加的参数，其中`-o Arch.pretrained=False`表示不使用预训练模型，`-o Global.device=gpu`表示使用GPU进行训练。如果希望使用CPU进行训练，则需要将`Global.device`设置为`cpu`。
更详细的训练配置，也可以直接修改模型对应的配置文件。具体配置参数参考[配置文档](config.md)。
@@ -37,9 +37,9 @@ python tools/train.py \
* 如果在训练中使用了mixup或者cutmix的数据增广方式，那么日志中将不会打印top-1与top-k（默认为5）信息：
```
...
- epoch:0 , train step:20 , loss: 4.53660, lr: 0.003750, batch_cost: 1.23101 s, reader_cost: 0.74311 s, ips: 25.99489 images/sec, eta: 0:12:43
+ [Train][Epoch 3/20][Avg]CELoss: 6.46287, loss: 6.46287
...
- END epoch:1 valid top1: 0.01569, top5: 0.06863, loss: 4.61747, batch_cost: 0.26155 s, reader_cost: 0.16952 s, batch_cost_sum: 10.72348 s, ips: 76.46772 images/sec.
+ [Eval][Epoch 3][Avg]CELoss: 5.94309, loss: 5.94309, top1: 0.01961, top5: 0.07941
...
```
@@ -47,9 +47,9 @@ python tools/train.py \
```
...
- epoch:0 , train step:30 , top1: 0.06250, top5: 0.09375, loss: 4.62766, lr: 0.003728, batch_cost: 0.64089 s, reader_cost: 0.18857 s, ips: 49.93080 images/sec, eta: 0:06:18
+ [Train][Epoch 3/20][Avg]CELoss: 6.12570, loss: 6.12570, top1: 0.01765, top5: 0.06961
...
- END epoch:0 train top1: 0.01310, top5: 0.04738, loss: 4.65124, batch_cost: 0.64089 s, reader_cost: 0.18857 s, batch_cost_sum: 13.45863 s, ips: 49.93080 images/sec.
+ [Eval][Epoch 3][Avg]CELoss: 5.40727, loss: 5.40727, top1: 0.07549, top5: 0.20980
...
```
@@ -60,13 +60,13 @@ python tools/train.py \
根据自己的数据集路径设置好配置文件后，可以通过加载预训练模型的方式进行微调，如下所示。
```
-python tools/train.py \
- -c configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
- -o pretrained_model="./pretrained/MobileNetV3_large_x1_0_pretrained" \
- -o use_gpu=True
+python3 tools/train.py \
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml \
+ -o Arch.pretrained=True \
+ -o Global.device=gpu
```
-其中`-o pretrained_model`用于设置加载预训练模型权重文件的地址，使用时需要换成自己的预训练模型权重文件的路径，也可以直接在配置文件中修改该路径。
+其中`Arch.pretrained`设置为`True`表示加载ImageNet的预训练模型，此外，`Arch.pretrained`也可以指定具体的模型权重文件的地址，使用时需要换成自己的预训练模型权重文件的路径。
我们也提供了大量基于`ImageNet-1k`数据集的预训练模型，模型列表及下载地址详见[模型库概览](../models/models_intro.md)。
@@ -76,28 +76,29 @@ python tools/train.py \
如果训练任务因为其他原因被终止，也可以加载断点权重文件，继续训练：
```
-python tools/train.py \
- -c configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
- -o checkpoints="./output/MobileNetV3_large_x1_0/5/ppcls" \
- -o last_epoch=5 \
- -o use_gpu=True
+python3 tools/train.py \
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml \
+ -o Global.checkpoints="./output/MobileNetV3_large_x1_0/epoch_5" \
+ -o Optimizer.lr.last_epoch=5 \
+ -o Global.device=gpu
```
其中配置文件不需要做任何修改，只需要在继续训练时设置`checkpoints`参数即可，表示加载的断点权重文件路径，使用该参数会同时加载保存的断点权重和学习率、优化器等信息。
**注意**：
-* 参数`-o last_epoch=5`表示将上一次训练轮次数记为`5`，即本次训练轮次数从`6`开始计算，该值默认为-1，表示本次训练轮次数从`0`开始计算。
+* 参数`-o Optimizer.lr.last_epoch=5`表示将上一次训练轮次数记为`5`，即本次训练轮次数从`6`开始计算，该值默认为-1，表示本次训练轮次数从`0`开始计算。
+
+* `-o Global.checkpoints`参数无需包含断点权重文件的后缀名，上述训练命令会在训练过程中生成如下所示的断点权重文件，若想从断点`5`继续训练，则`Global.checkpoints`参数只需设置为`"../output/MobileNetV3_large_x1_0/epoch_5"`，PaddleClas会自动补充后缀名。
-* `-o checkpoints`参数无需包含断点权重文件的后缀名，上述训练命令会在训练过程中生成如下所示的断点权重文件，若想从断点`5`继续训练，则`checkpoints`参数只需设置为`"./output/MobileNetV3_large_x1_0_gpupaddle/5/ppcls"`，PaddleClas会自动补充后缀名。
```shell
- output/
- └── MobileNetV3_large_x1_0
- ├── 0
- │ ├── ppcls.pdopt
- │ └── ppcls.pdparams
- ├── 1
- │ ├── ppcls.pdopt
- │ └── ppcls.pdparams
+ output
+ ├── MobileNetV3_large_x1_0
+ │ ├── best_model.pdopt
+ │ ├── best_model.pdparams
+ │ ├── best_model.pdstates
+ │ ├── epoch_1.pdopt
+ │ ├── epoch_1.pdparams
+ │ ├── epoch_1.pdstates
.
.
.
@@ -109,20 +110,18 @@ python tools/train.py \
可以通过以下命令进行模型评估。
```bash
-python tools/eval.py \
- -c ./configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
- -o pretrained_model="./output/MobileNetV3_large_x1_0/best_model/ppcls"\
- -o load_static_weights=False
+python3 tools/eval.py \
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml \
+ -o Global.pretrained_model=./output/MobileNetV3_large_x1_0/best_model
```
-上述命令将使用`./configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml`作为配置文件，对上述训练得到的模型`./output/MobileNetV3_large_x1_0/best_model/ppcls`进行评估。你也可以通过更改配置文件中的参数来设置评估，也可以通过`-o`参数更新配置，如上所示。
+上述命令将使用`./configs/quick_start/MobileNetV3_large_x1_0.yaml`作为配置文件，对上述训练得到的模型`./output/MobileNetV3_large_x1_0/best_model`进行评估。你也可以通过更改配置文件中的参数来设置评估，也可以通过`-o`参数更新配置，如上所示。
可配置的部分评估参数说明如下：
-* `ARCHITECTURE.name`：模型名称
-* `pretrained_model`：待评估的模型文件路径
-* `load_static_weights`：待评估模型是否为静态图模型
+* `Arch.name`：模型名称
+* `Global.pretrained_model`：待评估的模型文件路径
-**注意：** 如果模型为动态图模型，则在加载待评估模型时，需要指定模型文件的路径，但无需包含文件后缀名，PaddleClas会自动补齐`.pdparams`的后缀，如[1.3 模型恢复训练](#1.3)。
+**注意：** 在加载待评估模型时，需要指定模型文件的路径，但无需包含文件后缀名，PaddleClas会自动补齐`.pdparams`的后缀，如[1.3 模型恢复训练](#1.3)。
## 2. 基于Linux+GPU的模型训练与评估
@@ -138,24 +137,12 @@ python tools/eval.py \
export CUDA_VISIBLE_DEVICES=0,1,2,3
-python -m paddle.distributed.launch \
+python3 -m paddle.distributed.launch \
--gpus="0,1,2,3" \
tools/train.py \
- -c ./configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml
```
-其中，`-c`用于指定配置文件的路径，可通过配置文件修改相关训练配置信息，也可以通过添加`-o`参数来更新配置：
-
-```bash
-python -m paddle.distributed.launch \
- --gpus="0,1,2,3" \
- tools/train.py \
- -c ./configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
- -o pretrained_model="" \
- -o use_gpu=True
-```
-`-o`用于指定需要修改或者添加的参数，其中`-o pretrained_model=""`表示不使用预训练模型，`-o use_gpu=True`表示使用GPU进行训练。
-
输出日志信息的格式同上，详见[1.1 模型训练](#1.1)。
### 2.2 模型微调
@@ -165,14 +152,14 @@ python -m paddle.distributed.launch \
```
export CUDA_VISIBLE_DEVICES=0,1,2,3
-python -m paddle.distributed.launch \
+python3 -m paddle.distributed.launch \
--gpus="0,1,2,3" \
tools/train.py \
- -c ./configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
- -o pretrained_model="./pretrained/MobileNetV3_large_x1_0_pretrained"
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml \
+ -o Arch.pretrained=True
```
-其中`pretrained_model`用于设置加载预训练权重文件的路径，使用时需要换成自己的预训练模型权重文件路径，也可以直接在配置文件中修改该路径。
+其中`Arch.pretrained`为`True`或`False`，当然也可以设置加载预训练权重文件的路径，使用时需要换成自己的预训练模型权重文件路径，也可以直接在配置文件中修改该路径。
30分钟玩转PaddleClas[尝鲜版](./quick_start_new_user.md)与[进阶版](./quick_start_professional.md)中包含大量模型微调的示例，可以参考该章节在特定的数据集上进行模型微调。
@@ -185,16 +172,16 @@ python -m paddle.distributed.launch \
```
export CUDA_VISIBLE_DEVICES=0,1,2,3
-python -m paddle.distributed.launch \
+python3 -m paddle.distributed.launch \
--gpus="0,1,2,3" \
tools/train.py \
- -c ./configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
- -o checkpoints="./output/MobileNetV3_large_x1_0/5/ppcls" \
- -o last_epoch=5 \
- -o use_gpu=True
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml \
+ -o Global.checkpoints="./output/MobileNetV3_large_x1_0/epoch_5" \
+ -o Optimizer.lr.last_epoch=5 \
+ -o Global.device=gpu
```
-其中配置文件不需要做任何修改，只需要在训练时设置`checkpoints`参数与`last_epoch`参数即可，该参数表示加载的断点权重文件路径，使用该参数会同时加载保存的模型参数权重和学习率、优化器等信息，详见[1.3 模型恢复训练](#1.3)。
+其中配置文件不需要做任何修改，只需要在训练时设置`Global.checkpoints`参数与`Optimizer.lr.last_epoch`参数即可，该参数表示加载的断点权重文件路径，使用该参数会同时加载保存的模型参数权重和学习率、优化器等信息，详见[1.3 模型恢复训练](#1.3)。
### 2.4 模型评估
@@ -202,10 +189,11 @@ python -m paddle.distributed.launch \
可以通过以下命令进行模型评估。
```bash
-python tools/eval.py \
- -c ./configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml \
- -o pretrained_model="./output/MobileNetV3_large_x1_0/best_model/ppcls"\
- -o load_static_weights=False
+export CUDA_VISIBLE_DEVICES=0,1,2,3
+python3 -m paddle.distributed.launch \
+ tools/eval.py \
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml \
+ -o Global.pretrained_model=./output/MobileNetV3_large_x1_0/best_model
```
参数说明详见[1.4 模型评估](#1.4)。
@@ -217,26 +205,16 @@ python tools/eval.py \
模型训练完成之后，可以加载训练得到的预训练模型，进行模型预测。在模型库的 `tools/infer/infer.py` 中提供了完整的示例，只需执行下述命令即可完成模型预测：
```python
-python tools/infer/infer.py \
- -i 待预测的图片文件路径 \
- --model MobileNetV3_large_x1_0 \
- --pretrained_model "./output/MobileNetV3_large_x1_0/best_model/ppcls" \
- --use_gpu True \
- --class_num 1000
+
+python3 tools/infer.py \
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml \
+ -o Infer.infer_imgs=dataset/flowers102/jpg/image_00001.jpg \
+ -o Global.pretrained_model=./output/MobileNetV3_large_x1_0/best_model
```
参数说明：
-+ `image_file`(简写 i)：待预测的图片文件路径或者批量预测时的图片文件夹，如 `./test.jpeg`
-+ `model`：模型名称，如 `MobileNetV3_large_x1_0`
-+ `pretrained_model`：模型权重文件路径，如 `./output/MobileNetV3_large_x1_0/best_model/ppcls`
-+ `use_gpu` : 是否开启GPU训练，默认值：`True`
-+ `class_num` : 类别数，默认为1000，需要根据自己的数据进行修改。
-+ `resize_short`: 对输入图像进行等比例缩放，表示最短边的尺寸，默认值：`256`
-+ `resize`: 对`resize_short`操作后的进行居中裁剪，表示裁剪的尺寸，默认值：`224`
-+ `pre_label_image` : 是否对图像数据进行预标注，默认值：`False`
-+ `pre_label_out_idr` : 预标注图像数据的输出文件夹，当`pre_label_image=True`时，会在该文件夹下面生成很多个子文件夹，每个文件夹名称为类别id，其中存储模型预测属于该类别的所有图像。
-
-**注意**: 如果使用`Transformer`系列模型，如`DeiT_***_384`, `ViT_***_384`等，请注意模型的输入数据尺寸，需要设置参数`resize_short=384`, `resize=384`。
++ `Infer.infer_imgs`：待预测的图片文件路径或者批量预测时的图片文件夹。
++ `Global.pretrained_model`：模型权重文件路径，如 `./output/MobileNetV3_large_x1_0/best_model`
@@ -246,42 +224,39 @@ python tools/infer/infer.py \
首先，对训练好的模型进行转换：
```bash
-python tools/export_model.py \
- --model MobileNetV3_large_x1_0 \
- --pretrained_model ./output/MobileNetV3_large_x1_0/best_model/ppcls \
- --output_path ./inference \
- --class_dim 1000
+python3 tools/export_model.py \
+ -c ./ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml \
+ -o Global.pretrained_model=output/MobileNetV3_large_x1_0/best_model
```
-其中，参数`--model`用于指定模型名称，`--pretrained_model`用于指定模型文件路径，该路径仍无需包含模型文件后缀名（如[1.3 模型恢复训练](#1.3)），`--output_path`用于指定转换后模型的存储路径，`class_dim`表示模型所包含的类别数，默认为1000。
-**注意**：
-1. `--output_path`表示输出的inference模型文件夹路径，若`--output_path=./inference`，则会在`inference`文件夹下生成`inference.pdiparams`、`inference.pdmodel`和`inference.pdiparams.info`文件。
-2. 可以通过设置参数`--img_size`指定模型输入图像的`shape`，默认为`224`，表示图像尺寸为`224*224`，请根据实际情况修改。
+其中，`Global.pretrained_model`用于指定模型文件路径，该路径仍无需包含模型文件后缀名（如[1.3 模型恢复训练](#1.3)）。
+
上述命令将生成模型结构文件（`inference.pdmodel`）和模型权重文件（`inference.pdiparams`），然后可以使用预测引擎进行推理：
+进入deploy目录下：
+
```bash
-python tools/infer/predict.py \
- --image_file 图片路径 \
- --model_file "./inference/inference.pdmodel" \
- --params_file "./inference/inference.pdiparams" \
- --use_gpu=True \
- --use_tensorrt=False
+cd deploy
```
+
+执行命令进行预测，由于默认class_id_map_file是ImageNet数据集的映射文件，所以此处需要置None。
+
+```bash
+python3 python/predict_cls.py \
+ -c configs/inference_cls.yaml \
+ -o Global.infer_imgs=../dataset/flowers102/jpg/image_00001.jpg \
+ -o Global.inference_model_dir=../inference/ \
+ -o PostProcess.class_id_map_file=None
+
+
其中：
-+ `image_file`：待预测的图片文件路径，如 `./test.jpeg`
-+ `model_file`：模型结构文件路径，如 `./inference/inference.pdmodel`
-+ `params_file`：模型权重文件路径，如 `./inference/inference.pdiparams`
-+ `use_tensorrt`：是否使用 TesorRT 预测引擎，默认值：`True`
-+ `use_gpu`：是否使用 GPU 预测，默认值：`True`
-+ `enable_mkldnn`：是否启用`MKL-DNN`加速，默认为`False`。注意`enable_mkldnn`与`use_gpu`同时为`True`时，将忽略`enable_mkldnn`，而使用GPU运行。
-+ `resize_short`: 对输入图像进行等比例缩放，表示最短边的尺寸，默认值：`256`
-+ `resize`: 对`resize_short`操作后的进行居中裁剪，表示裁剪的尺寸，默认值：`224`
-+ `enable_calc_topk`: 是否计算预测结果的Topk精度指标，默认为`False`，
-+ `gt_label_path`: 图像文件名以及真值标签文件，当`enable_calc_topk`为True时生效，用于读取待预测的图像列表及其标签。
++ `Global.infer_imgs`：待预测的图片文件路径。
++ `Global.inference_model_dir`：inference模型结构文件路径，如 `../inference/inference.pdmodel`
++ `Global.use_tensorrt`：是否使用 TesorRT 预测引擎，默认值：`False`
++ `Global.use_gpu`：是否使用 GPU 预测，默认值：`True`
++ `Global.enable_mkldnn`：是否启用`MKL-DNN`加速，默认为`False`。注意`enable_mkldnn`与`use_gpu`同时为`True`时，将忽略`enable_mkldnn`，而使用GPU运行。
++ `Global.use_fp16`：是否启用`FP16`，默认为`False`。
-
-**注意**: 如果使用`Transformer`系列模型，如`DeiT_***_384`, `ViT_***_384`等，请注意模型的输入数据尺寸，需要设置参数`resize_short=384`, `resize=384`。
-
-* 如果你希望评测模型速度，建议使用该脚本(`tools/infer/predict.py`)，同时开启TensorRT加速预测。
+* 如果你希望提升评测模型速度，使用gpu评测时，建议开启TensorRT加速预测，使用cpu评测时，建议开启MKL-DNN加速预测。
diff --git a/docs/zh_CN/tutorials/quick_start_community.md b/docs/zh_CN/tutorials/quick_start_community.md
index 69868ae00..a39686fb2 100644
--- a/docs/zh_CN/tutorials/quick_start_community.md
+++ b/docs/zh_CN/tutorials/quick_start_community.md
@@ -51,34 +51,30 @@ train/n01440764/n01440764_10027.JPEG 0
对于读入的数据，需要通过数据转换，将原始的图像数据进行转换。训练时，标准的数据预处理包含：`DecodeImage`, `RandCropImage`, `RandFlipImage`, `NormalizeImage`, `ToCHWImage`。在配置文件中体现如下，数据预处理主要包含在`transforms`字段中，以列表形式呈现，会按照顺序对数据依次做这些转换。
```yaml
-TRAIN:
- batch_size: 256 # 所有训练设备上的总batch size
- num_workers: 4 # 训练时每块设备上的进程数
- file_list: "./dataset/ILSVRC2012/train_list.txt" # 训练标签文件
- data_dir: "./dataset/ILSVRC2012/" # 训练图片文件夹
- shuffle_seed: 0 # 随机打散的种子数
- transforms:
- - DecodeImage: # 对图像文件进行解码，转成numpy矩阵
+DataLoader:
+ Train:
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/ILSVRC2012/
+ cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+ transform_ops:
+ - DecodeImage:
to_rgb: True
channel_first: False
- - RandCropImage: # 对图像做随机裁剪
+ - RandCropImage:
size: 224
- - RandFlipImage: # 对图像做随机翻转
+ - RandFlipImage:
flip_code: 1
- - NormalizeImage: # 对图像做归一化
- scale: 1./255.
+ - NormalizeImage:
+ scale: 1.0/255.0
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- - ToCHWImage: # 将图像从HWC格式转成CHW格式
- mix:
- - MixupOperator: # mixup数据增广，在全局配置use_mix=True时生效
- alpha: 0.2
```
-PaddleClas中也包含了`AutoAugment`, `RandAugment`等数据增广方法，也可以通过在配置文件中配置，从而添加到训练过程的数据预处理中。每个数据转换的方法均以类实现，方便迁移和复用，更多的数据处理具体实现过程可以参考：`ppcls/data/imaug/operators.py`。
+PaddleClas中也包含了`AutoAugment`, `RandAugment`等数据增广方法，也可以通过在配置文件中配置，从而添加到训练过程的数据预处理中。每个数据转换的方法均以类实现，方便迁移和复用，更多的数据处理具体实现过程可以参考`ppcls/data/preprocess/ops/`下的代码。
-对于组成一个batch的数据，也可以使用mixup或者cutmix等方法进行数据增广。PaddleClas中集成了`MixupOperator`, `CutmixOperator`, `FmixOperator`等基于batch的数据增广方法，可以在配置文件中配置mix参数进行配置，更加具体的实现可以参考`ppcls/data/imaug/batch_operators.py`。
+对于组成一个batch的数据，也可以使用mixup或者cutmix等方法进行数据增广。PaddleClas中集成了`MixupOperator`, `CutmixOperator`, `FmixOperator`等基于batch的数据增广方法，可以在配置文件中配置mix参数进行配置，更加具体的实现可以参考`ppcls/data/preprocess/batch_ops/batch_operators.py`。
图像分类中，数据后处理主要为`argmax`操作，在此不再赘述。
@@ -87,69 +83,47 @@ PaddleClas中也包含了`AutoAugment`, `RandAugment`等数据增广方法，也
在配置文件中，模型结构定义如下
```yaml
-ARCHITECTURE:
- name: "EfficientNetB0"
- params: # 模型需要传入的额外参数，如果没有可不填
- padding_type : "SAME"
- override_params:
- drop_connect_rate: 0.1
+Arch:
+ name: ResNet50
+ pretrained: False
+ use_ssld: False
```
+`Arch.name`表示模型名称，`Arch.pretrained`表示是否添加预训练模型。所有的模型名称均在`ppcls/arch/backbone/__init__.py`中定义。
-`ARCHITECTURE.name`表示模型名称，`ARCHITECTURE.params`表示需要额外传入的参数，默认为空。所有的模型名称均在`/ppcls/modeling/architectures/__init__.py`中定义。
-
-对应的，在`tools/program.py`中，通过`create_model`方法创建模型对象。
+对应的，在`ppcls/arch/__init__.py`中，通过`build_model`方法创建模型对象。
```python
-def create_model(architecture, classes_num):
- name = architecture["name"]
- params = architecture.get("params", {})
- return architectures.__dict__[name](class_dim=classes_num, **params)
+def build_model(config):
+ config = copy.deepcopy(config)
+ model_type = config.pop("name")
+ mod = importlib.import_module(__name__)
+ arch = getattr(mod, model_type)(**config)
+ return arch
```
* 损失函数
-PaddleClas中，包含了`CELoss`, `MixCELoss`, `GoogLeNetLoss`, `JSDivLoss`, `MultiLabelLoss`等损失函数，均定义在`ppcls/modeling/loss.py`中。
+PaddleClas中，包含了`CELoss`, `JSDivLoss`, `TripletLoss`, `CenterLoss`等损失函数，均定义在`ppcls/loss`中。
-在`tools/program.py`文件中，使用`create_loss`构建模型的损失函数，不同训练策略中所需要的损失函数与计算方法不同，PaddleClas在构建损失函数过程中，主要考虑了以下几个因素。
+在`ppcls/loss/__init__.py`文件中，使用`CombinedLoss`来构建及合并损失函数，不同训练策略中所需要的损失函数与计算方法不同，PaddleClas在构建损失函数过程中，主要考虑了以下几个因素。
1. 是否使用label smooth
2. 是否使用mixup或者cutmix
3. 是否使用蒸馏方法进行训练
-4. 是否进行多标签训练
+4. 是否是训练metric learning
-```python
-def create_loss(feeds,
- out,
- architecture,
- classes_num=1000,
- epsilon=None,
- use_mix=False,
- use_distillation=False,
- multilabel=False):
- if architecture["name"] == "GoogLeNet":
- assert len(out) == 3, "GoogLeNet should have 3 outputs"
- loss = GoogLeNetLoss(class_dim=classes_num, epsilon=epsilon)
- return loss(out[0], out[1], out[2], feeds["label"])
- if use_distillation:
- assert len(out) == 2, ("distillation output length must be 2, "
- "but got {}".format(len(out)))
- loss = JSDivLoss(class_dim=classes_num, epsilon=epsilon)
- return loss(out[1], out[0])
+用户可以在配置文件中指定损失函数的类型及权重，如在训练中添加TripletLossV2，配置文件如下：
- if use_mix:
- loss = MixCELoss(class_dim=classes_num, epsilon=epsilon)
- feed_y_a = feeds['y_a']
- feed_y_b = feeds['y_b']
- feed_lam = feeds['lam']
- return loss(out, feed_y_a, feed_y_b, feed_lam)
- else:
- if not multilabel:
- loss = CELoss(class_dim=classes_num, epsilon=epsilon)
- else:
- loss = MultiLabelLoss(class_dim=classes_num, epsilon=epsilon)
- return loss(out, feeds["label"])
+```yaml
+Loss:
+ Train:
+ - CELoss:
+ weight: 1.0
+ - TripletLossV2:
+ weight: 1.0
+ margin: 0.5
```
* 优化器和学习率衰减、权重衰减策略
@@ -158,48 +132,53 @@ def create_loss(feeds,
权重衰减策略是一种比较常用的正则化方法，主要用于防止模型过拟合。PaddleClas中提供了`L1Decay`和`L2Decay`两种权重衰减策略。
-学习率衰减是图像分类任务中必不可少的精度提升训练方法，PaddleClas目前支持`Cosine`, `Piecewise`, `CosineWarmup`, `ExponentialWarmup`等学习率衰减策略。
+学习率衰减是图像分类任务中必不可少的精度提升训练方法，PaddleClas目前支持`Cosine`, `Piecewise`, `Linear`等学习率衰减策略。
-在配置文件中，优化器和权重衰减策略可以通过以下的字段进行配置。
+在配置文件中，优化器、权重衰减策略、学习率衰减策略可以通过以下的字段进行配置。
```yaml
-OPTIMIZER:
- function: 'Momentum' # Momentum优化器
- params:
- momentum: 0.9
- regularizer:
- function: 'L2' # L1 means L1Decay, L2 means L2Decay
- factor: 0.00010
+Optimizer:
+ name: Momentum
+ momentum: 0.9
+ lr:
+ name: Piecewise
+ learning_rate: 0.1
+ decay_epochs: [30, 60, 90]
+ values: [0.1, 0.01, 0.001, 0.0001]
+ regularizer:
+ name: 'L2'
+ coeff: 0.0001
```
-学习率衰减策略可以通过以下的字段进行配置。
-
-```yaml
-LEARNING_RATE:
- function: 'Piecewise' # Piecewise学习率衰减策略
- params:
- lr: 0.1 # 初始学习率
- decay_epochs: [30, 60, 90] # 学习率下降时对应的epoch数量
- gamma: 0.1 # 学习率衰减倍数
-```
-
-在`tools/program.py`中使用`create_optimizer`创建优化器和学习率对象。
+在`ppcls/optimizer/__init__.py`中使用`build_optimizer`创建优化器和学习率对象。
```python
-def create_optimizer(config, parameter_list=None):
- # create learning_rate instance
- lr_config = config['LEARNING_RATE']
- lr_config['params'].update({
- 'epochs': config['epochs'],
- 'step_each_epoch':
- config['total_images'] // config['TRAIN']['batch_size'],
- })
- lr = LearningRateBuilder(**lr_config)()
-
- # create optimizer instance
- opt_config = config['OPTIMIZER']
- opt = OptimizerBuilder(**opt_config)
- return opt(lr, parameter_list), lr
+def build_optimizer(config, epochs, step_each_epoch, parameters):
+ config = copy.deepcopy(config)
+ # step1 build lr
+ lr = build_lr_scheduler(config.pop('lr'), epochs, step_each_epoch)
+ logger.debug("build lr ({}) success..".format(lr))
+ # step2 build regularization
+ if 'regularizer' in config and config['regularizer'] is not None:
+ reg_config = config.pop('regularizer')
+ reg_name = reg_config.pop('name') + 'Decay'
+ reg = getattr(paddle.regularizer, reg_name)(**reg_config)
+ else:
+ reg = None
+ logger.debug("build regularizer ({}) success..".format(reg))
+ # step3 build optimizer
+ optim_name = config.pop('name')
+ if 'clip_norm' in config:
+ clip_norm = config.pop('clip_norm')
+ grad_clip = paddle.nn.ClipGradByNorm(clip_norm=clip_norm)
+ else:
+ grad_clip = None
+ optim = getattr(optimizer, optim_name)(learning_rate=lr,
+ weight_decay=reg,
+ grad_clip=grad_clip,
+ **config)(parameters=parameters)
+ logger.debug("build optimizer ({}) success..".format(optim))
+ return optim, lr
```
不同优化器和权重衰减策略均以类的形式实现，具体实现可以参考文件`ppcls/optimizer/optimizer.py`；不同的学习率衰减策略可以参考文件`ppcls/optimizer/learning_rate.py`。
@@ -210,27 +189,22 @@ def create_optimizer(config, parameter_list=None):
模型在训练的时候，可以设置模型保存的间隔，也可以选择每隔若干个epoch对验证集进行评估，从而可以保存在验证集上精度最佳的模型。配置文件中，可以通过下面的字段进行配置。
```yaml
-save_interval: 1 # 模型保存的epoch间隔
-validate: True # 是否进行训练时评估
-valid_interval: 1 # 评估的epoch间隔
+Global:
+ save_interval: 1 # 模型保存的epoch间隔
+ eval_during_train: True # 是否进行训练时评估
+ eval_interval: 1 # 评估的epoch间隔
```
模型存储是通过 Paddle 框架的 `paddle.save()` 函数实现的，存储的是模型的 persistable 版本，便于继续训练。具体实现如下
```python
-def save_model(net, optimizer, model_path, epoch_id, prefix='ppcls'):
- # just save model in trainer_id=0
- if paddle.distributed.get_rank() != 0:
- return
+ef save_model(program, model_path, epoch_id, prefix='ppcls'):
model_path = os.path.join(model_path, str(epoch_id))
_mkdir_if_not_exist(model_path)
model_prefix = os.path.join(model_path, prefix)
- # save student model during distillation
- _save_student_model(net, model_prefix)
-
- paddle.save(net.state_dict(), model_prefix + ".pdparams")
- paddle.save(optimizer.state_dict(), model_prefix + ".pdopt")
- logger.info("Already save model in {}".format(model_path))
+ paddle.static.save(program, model_prefix)
+ logger.info(
+ logger.coloring("Already save model in {}".format(model_path), "HEADER"))
```
在保存的时候有两点需要注意：
diff --git a/docs/zh_CN/tutorials/quick_start_new_user.md b/docs/zh_CN/tutorials/quick_start_new_user.md
index 70e726752..4f1894ed6 100644
--- a/docs/zh_CN/tutorials/quick_start_new_user.md
+++ b/docs/zh_CN/tutorials/quick_start_new_user.md
@@ -75,20 +75,6 @@ cd ../../
### 预训练模型下载
-```shell
-# 创建文件夹pretrained文件夹并进入
-mkdir pretrained && cd pretrained
-# 下载预训练模型
-# 下载ResNet50_vd模型
-wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_pretrained.pdparams
-# 下载ShuffleNetV2_x0_25模型
-wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ShuffleNetV2_x0_25_pretrained.pdparams
-# 回到PaddleClas主目录
-cd ..
-```
-
-Windows操作如上提示，在PaddleClas根目录下创建相应文件夹，并下载好预训练模型后，放到此文件夹中。
-
### 训练模型
#### 使用CPU进行模型训练
@@ -99,20 +85,19 @@ Windows操作如上提示，在PaddleClas根目录下创建相应文件夹，并
```shell
#windows在cmd中进入PaddleClas根目录，执行此命令
-python tools/train.py -c ./configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml
+python tools/train.py -c ./ppcls/configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml
```
- `-c` 参数是指定训练的配置文件路径，训练的具体超参数可查看`yaml`文件
-- `yaml`文`use_gpu` 参数设置为`False`，即使用CPU进行训练（若不设置，此参数默认为`True`）
+- `yaml`文`Global.device` 参数设置为`cpu`，即使用CPU进行训练（若不设置，此参数默认为`True`）
- `yaml`文件中`epochs`参数设置为20，说明对整个数据集进行20个epoch迭代，预计训练20分钟左右（不同CPU，训练时间略有不同），此时训练模型不充分。若提高训练模型精度，请将此参数设大，如**40**，训练时间也会相应延长
##### 使用预训练模型
```shell
-python tools/train.py -c ./configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml -o pretrained_model="pretrained/ShuffleNetV2_x0_25_pretrained"
-```
+python tools/train.py -c ./ppcls/configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml -o Arch.pretrained=True
-- `-o` 参数加入预训练模型地址，注意：预训练模型路径不要加上：`.pdparams`
+- `-o` 参数可以选择为True或False，也可以是预训练模型存放路径，当选择为True时，预训练权重会自动下载到本地。注意：若为预训练模型路径，则不要加上：`.pdparams`
可以使用将使用与不使用预训练模型训练进行对比，观察loss的下降情况。
@@ -137,7 +122,7 @@ python tools/train.py -c ./configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml
##### 不使用预训练模型
```shell
-python tools/train.py -c ./configs/quick_start/ResNet50_vd.yaml
+python3 tools/train.py -c ./ppcls/configs/quick_start/ResNet50_vd.yaml
```
训练完成后，验证集的`Top1 Acc`曲线如下所示，最高准确率为0.2735。训练精度曲线下图所示
@@ -149,13 +134,12 @@ python tools/train.py -c ./configs/quick_start/ResNet50_vd.yaml
基于ImageNet1k分类预训练模型进行微调，训练脚本如下所示
```shell
-python tools/train.py -c ./configs/quick_start/ResNet50_vd_finetune.yaml
+python3 tools/train.py -c ./ppcls/configs/quick_start/ResNet50_vd.yaml -o Arch.pretrained=True
```
**注**：
- 此训练脚本使用GPU，如使用CPU可按照上文中[使用CPU进行模型训练](#使用CPU进行模型训练)所示，进行修改
-- 与[不使用预训练模型](#不使用预训练模型)的`yaml`文件的主要不同，此`ymal`文件中加入 `pretrained_model` 参数，此参数指明预训练模型的位置
验证集的`Top1 Acc`曲线如下所示，最高准确率为0.9402，加载预训练模型之后，flowers102数据集精度大幅提升，绝对精度涨幅超过65%。
@@ -167,35 +151,16 @@ python tools/train.py -c ./configs/quick_start/ResNet50_vd_finetune.yaml
```shell
cd $path_to_PaddleClas
-python tools/infer/infer.py --model ShuffleNetV2_x0_25 -i dataset/flowers102/jpg/image_00001.jpg --pretrained_model output/ShuffleNetV2_x0_25/best_model/ppcls --class_num 102 --use_gpu False
+python3 tools/infer.py -c ./ppcls/configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml -o Infer.infer_imgs=dataset/flowers102/jpg/image_00001.jpg -o Global.pretrained_model=output/ShuffleNetV2_x0_25/best_model
```
-其中主要参数如下：
-
-- `--model`：训练时使用擦网络模型，如 ShuffleNetV2_x0_25、ResNet50_vd，具体可查看训练时`yaml`文件中**ARCHITECTURE**下 **name**参数的值
-- `-i`：图像文件路径或者图像所在目录
-- `--pretrained_model`： 存放的模型权重位置。上述CPU训练过程中，最优模型存放位置如下：`output/ShuffleNetV2_x0_25/best_model/ppcls.pdparams`，此时此参数应如下填写：`output/ShuffleNetV2_x0_25/best_model/ppcls`，去掉`.pdparams`
-- `--class_num`：为图像类别数，`flowers102`数据集为102类。若用其他数据集，改成相应类别数即可
-- `--use_gpu`：是否使用GPU
-
`-i`输入为单张图像路径，运行成功后，示例结果如下：
-`File:image_00001.jpg, Top-1 result: class id(s): [72], score(s): [0.03]`
+`[{'class_ids': [76, 65, 34, 9, 69], 'scores': [0.91762, 0.01801, 0.00833, 0.0071, 0.00669], 'file_name': 'dataset/flowers102/jpg/image_00001.jpg', 'label_names': []}]`
`-i`输入为图像集所在目录，运行成功后，示例结果如下：
```txt
-File:image_02993.jpg, Top-1 result: class id(s): [77], score(s): [0.02]
-File:image_00448.jpg, Top-1 result: class id(s): [77], score(s): [0.02]
-File:image_08001.jpg, Top-1 result: class id(s): [77], score(s): [0.01]
-File:image_00804.jpg, Top-1 result: class id(s): [100], score(s): [0.02]
-File:image_01842.jpg, Top-1 result: class id(s): [100], score(s): [0.02]
-File:image_02790.jpg, Top-1 result: class id(s): [70], score(s): [0.05]
-File:image_03412.jpg, Top-1 result: class id(s): [100], score(s): [0.02]
-File:image_05196.jpg, Top-1 result: class id(s): [77], score(s): [0.02]
-File:image_06860.jpg, Top-1 result: class id(s): [70], score(s): [0.03]
-File:image_05312.jpg, Top-1 result: class id(s): [77], score(s): [0.02]
-File:image_05930.jpg, Top-1 result: class id(s): [100], score(s): [0.02]
-File:image_05711.jpg, Top-1 result: class id(s): [77], score(s): [0.01]
-File:image_01180.jpg, Top-1 result: class id(s): [70], score(s): [0.03]
+[{'class_ids': [76, 65, 34, 9, 69], 'scores': [0.91762, 0.01801, 0.00833, 0.0071, 0.00669], 'file_name': 'dataset/flowers102/jpg/image_00001.jpg', 'label_names': []}, {'class_ids': [76, 69, 34, 28, 9], 'scores': [0.77122, 0.06295, 0.02537, 0.02531, 0.0251], 'file_name': 'dataset/flowers102/jpg/image_00002.jpg', 'label_names': []}, {'class_ids': [99, 76, 81, 85, 16], 'scores': [0.26374, 0.20423, 0.07818, 0.06042, 0.05499], 'file_name': 'dataset/flowers102/jpg/image_00003.jpg', 'label_names': []}, {'class_ids': [9, 37, 34, 24, 76], 'scores': [0.17784, 0.16651, 0.14539, 0.12096, 0.04816], 'file_name': 'dataset/flowers102/jpg/image_00004.jpg', 'label_names': []}, {'class_ids': [76, 66, 91, 16, 13], 'scores': [0.95494, 0.00688, 0.00596, 0.00352, 0.00308], 'file_name': 'dataset/flowers102/jpg/image_00005.jpg', 'label_names': []}, {'class_ids': [76, 66, 34, 8, 43], 'scores': [0.44425, 0.07487, 0.05609, 0.05609, 0.03667], 'file_name': 'dataset/flowers102/jpg/image_00006.jpg', 'label_names': []}, {'class_ids': [86, 93, 81, 22, 21], 'scores': [0.44714, 0.13582, 0.07997, 0.0514, 0.03497], 'file_name': 'dataset/flowers102/jpg/image_00007.jpg', 'label_names': []}, {'class_ids': [13, 76, 81, 18, 97], 'scores': [0.26771, 0.1734, 0.06576, 0.0451, 0.03986], 'file_name': 'dataset/flowers102/jpg/image_00008.jpg', 'label_names': []}, {'class_ids': [34, 76, 8, 5, 9], 'scores': [0.67224, 0.31896, 0.00241, 0.00227, 0.00102], 'file_name': 'dataset/flowers102/jpg/image_00009.jpg', 'label_names': []}, {'class_ids': [76, 34, 69, 65, 66], 'scores': [0.95185, 0.01101, 0.00875, 0.00452, 0.00406], 'file_name': 'dataset/flowers102/jpg/image_00010.jpg', 'label_names': []}]
```
+其中，列表的长度为batch_size的大小。
diff --git a/docs/zh_CN/tutorials/quick_start_professional.md b/docs/zh_CN/tutorials/quick_start_professional.md
index c6a56395a..3fddab306 100644
--- a/docs/zh_CN/tutorials/quick_start_professional.md
+++ b/docs/zh_CN/tutorials/quick_start_professional.md
@@ -25,36 +25,6 @@ tar -xf CIFAR100.tar
cd ../
```
-#### 1.1.2 准备NUS-WIDE-SCENE
-
-* 创建并进入`dataset/NUS-WIDE-SCENE`目录，下载并解压NUS-WIDE-SCENE数据集。
-
-```shell
-mkdir dataset/NUS-WIDE-SCENE
-cd dataset/NUS-WIDE-SCENE
-wget https://paddle-imagenet-models-name.bj.bcebos.com/data/NUS-SCENE-dataset.tar
-tar -xf NUS-SCENE-dataset.tar
-```
-
-* 返回`PaddleClas`根目录
-
-```
-cd ../../
-```
-
-### 1.2 模型准备
-
-通过下面的命令下载所需要的预训练模型。
-
-```bash
-mkdir pretrained
-cd pretrained
-wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_pretrained.pdparams
-wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_pretrained.pdparams
-wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x1_0_pretrained.pdparams
-cd ../
-```
-
## 二、模型训练
@@ -69,8 +39,8 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3
python3 -m paddle.distributed.launch \
--gpus="0,1,2,3" \
tools/train.py \
- -c ./configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml \
- -o model_save_dir="output_CIFAR"
+ -c ./ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml \
+ -o Global.output_dir="output_CIFAR"
```
@@ -86,8 +56,9 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3
python3 -m paddle.distributed.launch \
--gpus="0,1,2,3" \
tools/train.py \
- -c ./configs/quick_start/professional/ResNet50_vd_CIFAR100_finetune.yaml \
- -o model_save_dir="output_CIFAR"
+ -c ./ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml \
+ -o Global.output_dir="output_CIFAR" \
+ -o Arch.pretrained=True
```
验证集最高准确率为0.718左右，加载预训练模型之后，CIFAR100数据集精度大幅提升，绝对精度涨幅30\%。
@@ -99,8 +70,10 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3
python3 -m paddle.distributed.launch \
--gpus="0,1,2,3" \
tools/train.py \
- -c ./configs/quick_start/professional/ResNet50_vd_ssld_CIFAR100_finetune.yaml \
- -o model_save_dir="output_CIFAR"
+ -c ./ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml \
+ -o Global.output_dir="output_CIFAR" \
+ -o Arch.pretrained=True \
+ -o Arch.use_ssld=True
```
最终CIFAR100验证集上精度指标为0.73，相对于79.12\%预训练模型的微调结构，新数据集指标可以再次提升1.2\%。
@@ -112,31 +85,14 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3
python3 -m paddle.distributed.launch \
--gpus="0,1,2,3" \
tools/train.py \
- -c ./configs/quick_start/professional/MobileNetV3_large_x1_0_CIFAR100_finetune.yaml \
- -o model_save_dir="output_CIFAR"
+ -c ./ppcls/configs/quick_start/professional/MobileNetV3_large_x1_0_CIFAR100_finetune.yaml \
+ -o Global.output_dir="output_CIFAR" \
+ -o Arch.pretrained=True
```
验证集最高准确率为0.601左右, 较ResNet50_vd低近12%。
-### 2.2 多标签训练
-
-* 基于ImageNet1k分类预训练模型进行微调NUS-WIDE-SCENE数据集，该是数据集NUS-WIDE的一个子集，类别数目为33类，图片总数是17463张，训练脚本如下所示。
-
-```shell
-export CUDA_VISIBLE_DEVICES=0,1,2,3
-python3 -m paddle.distributed.launch \
- --gpus="0,1,2,3" \
- tools/train.py \
- -c ./configs/quick_start/ResNet50_vd_multilabel.yaml \
- -o model_save_dir="output_NUS-WIDE-SCENE"
-```
-
-训练10epoch之后，验证集最好的准确率应该在0.95左右。
-
-* 零基础训练(不加载预训练模型)只需要将配置文件中的`pretrained_model`置为`""`即可。
-
-
## 三、数据增广
PaddleClas包含了很多数据增广的方法，如Mixup、Cutout、RandomErasing等，具体的方法可以参考[数据增广的章节](../advanced_tutorials/image_augmentation/ImageAugment.md)。
@@ -150,8 +106,8 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3
python3 -m paddle.distributed.launch \
--gpus="0,1,2,3" \
tools/train.py \
- -c ./configs/quick_start/professional/ResNet50_vd_mixup_CIFAR100_finetune.yaml \
- -o model_save_dir="output_CIFAR"
+ -c ./ppcls/configs/quick_start/professional/ResNet50_vd_mixup_CIFAR100_finetune.yaml \
+ -o Global.output_dir="output_CIFAR"
```
@@ -161,7 +117,7 @@ python3 -m paddle.distributed.launch \
* **注意**
- * 其他数据增广的配置文件可以参考`configs/DataAugment`中的配置文件。
+ * 其他数据增广的配置文件可以参考`ppcls/configs/DataAugment`中的配置文件。
* 训练CIFAR100的迭代轮数较少，因此进行训练时，验证集的精度指标可能会有1\%左右的波动。
@@ -172,18 +128,42 @@ python3 -m paddle.distributed.launch \
PaddleClas包含了自研的SSLD知识蒸馏方案，具体的内容可以参考[知识蒸馏章节](../advanced_tutorials/distillation/distillation.md)本小节将尝试使用知识蒸馏技术对MobileNetV3_large_x1_0模型进行训练，使用`2.1.2小节`训练得到的ResNet50_vd模型作为蒸馏所用的教师模型，首先将`2.1.2小节`训练得到的ResNet50_vd模型保存到指定目录，脚本如下。
```shell
-cp -r output_CIFAR/ResNet50_vd/best_model/ ./pretrained/CIFAR100_R50_vd_final/
+mkdir pretrained
+cp -r output_CIFAR/ResNet50_vd/best_model.pdparams ./pretrained/
```
-配置文件中数据数量、模型结构、预训练地址以及训练的数据配置如下：
+配置文件中模型名字、教师模型哈学生模型的配置、预训练地址配置以及freeze_params配置如下，其中freeze_params_list中的两个值分别代表教师模型和学生模型是否冻结参数训练。
```yaml
-total_images: 50000
-ARCHITECTURE:
- name: 'ResNet50_vd_distill_MobileNetV3_large_x1_0'
-pretrained_model:
- - "./pretrained/CIFAR100_R50_vd_final/ppcls"
- - "./pretrained/MobileNetV3_large_x1_0_pretrained/”
+Arch:
+ name: "DistillationModel"
+ # if not null, its lengths should be same as models
+ pretrained_list:
+ # if not null, its lengths should be same as models
+ freeze_params_list:
+ - True
+ - False
+ models:
+ - Teacher:
+ name: ResNet50_vd
+ pretrained: "./pretrained/best_model"
+ - Student:
+ name: MobileNetV3_large_x1_0
+ pretrained: True
+```
+
+Loss配置如下，其中训练Loss是学生模型的输出和教师模型的输出的交叉熵、验证Loss是学生模型的输出和真实标签的交叉熵。
+```yaml
+Loss:
+ Train:
+ - DistillationCELoss:
+ weight: 1.0
+ model_name_pairs:
+ - ["Student", "Teacher"]
+ Eval:
+ - DistillationGTCELoss:
+ weight: 1.0
+ model_names: ["Student"]
```
最终的训练脚本如下所示。
@@ -193,8 +173,8 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3
python3 -m paddle.distributed.launch \
--gpus="0,1,2,3" \
tools/train.py \
- -c ./configs/quick_start/professional/R50_vd_distill_MV3_large_x1_0_CIFAR100.yaml \
- -o model_save_dir="output_CIFAR"
+ -c ./ppcls/configs/quick_start/professional/R50_vd_distill_MV3_large_x1_0_CIFAR100.yaml \
+ -o Global.output_dir="output_CIFAR"
```
@@ -217,20 +197,19 @@ python3 -m paddle.distributed.launch \
```bash
python3 tools/eval.py \
- -c ./configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml \
- -o pretrained_model="./output_CIFAR/ResNet50_vd/best_model/ppcls"
+ -c ./ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml \
+ -o Global.pretrained_model="output_CIFAR/ResNet50_vd/best_model"
```
#### 5.1.2 单标签分类模型预测
-模型训练完成之后，可以加载训练得到的预训练模型，进行模型预测。在模型库的 `tools/infer/infer.py` 中提供了完整的示例，只需执行下述命令即可完成模型预测：
+模型训练完成之后，可以加载训练得到的预训练模型，进行模型预测。在模型库的 `tools/infer.py` 中提供了完整的示例，只需执行下述命令即可完成模型预测：
```python
-python3 tools/infer/infer.py \
- -i "./dataset/CIFAR100/test/0/0001.png" \
- --model ResNet50_vd \
- --pretrained_model "./output_CIFAR/ResNet50_vd/best_model/ppcls" \
- --use_gpu True
+python3 tools/infer.py \
+ -c ./ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml \
+ -o Infer.infer_imgs=./dataset/CIFAR100/test/0/0001.png \
+ -o Global.pretrained_model=output_CIFAR/ResNet50_vd/best_model
```
@@ -241,53 +220,41 @@ python3 tools/infer/infer.py \
```bash
python3 tools/export_model.py \
- --model ResNet50_vd \
- --pretrained_model ./output_CIFAR/ResNet50_vd/best_model/ppcls \
- --output_path ./inference \
- --class_dim 100 \
- --img_size 32
+ -c ./ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml \
+ -o Global.pretrained_model=output_CIFAR/ResNet50_vd/best_model
```
-其中，参数`--model`用于指定模型名称，`--pretrained_model`用于指定模型文件路径，`--output_path`用于指定转换后模型的存储路径。
+* 默认会在`inference`文件夹下生成`inference.pdiparams`、`inference.pdmodel`和`inference.pdiparams.info`文件。
-* **注意**：
- * `--output_path`表示输出的inference模型文件夹路径，若`--output_path=./inference`，则会在`inference`文件夹下生成`inference.pdiparams`、`inference.pdmodel`和`inference.pdiparams.info`文件。
+使用预测引擎进行推理：
- * 可以通过设置参数`--img_size`指定模型输入图像的`shape`，默认为`224`，表示图像尺寸为`224*224`，请根据实际情况修改。
-
-上述命令将生成模型结构文件（`inference.pdmodel`）和模型权重文件（`inference.pdiparams`），然后可以使用预测引擎进行推理：
+进入deploy目录下：
```bash
-python3 tools/infer/predict.py \
- --image_file "./dataset/CIFAR100/test/0/0001.png" \
- --model_file "./inference/inference.pdmodel" \
- --params_file "./inference/inference.pdiparams" \
- --use_gpu=True \
- --use_tensorrt=False
+cd deploy
+```
+更改inference_cls.yaml文件，由于训练CIFAR100采用的分辨率是32x32，所以需要改变相关的分辨率，最终配置文件中的图像预处理如下：
+
+```yaml
+PreProcess:
+ transform_ops:
+ - ResizeImage:
+ resize_short: 36
+ - CropImage:
+ size: 32
+ - NormalizeImage:
+ scale: 0.00392157
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ - ToCHWImage:
```
-### 5.2 多标签分类模型评估与预测
-
-#### 5.2.1 多标签分类模型评估
-
-训练好模型之后，可以通过以下命令实现对模型精度的评估。
+执行命令进行预测，由于默认class_id_map_file是ImageNet数据集的映射文件，所以此处需要置None。
```bash
-python3 tools/eval.py \
- -c ./configs/quick_start/ResNet50_vd_multilabel.yaml \
- -o pretrained_model="./output_NUS-WIDE-SCENE/ResNet50_vd/best_model/ppcls"
-```
-
-评估指标采用mAP，验证集的mAP应该在0.57左右。
-
-#### 5.2.2 多标签分类模型预测
-
-```bash
-python3 tools/infer/infer.py \
- -i "./dataset/NUS-WIDE-SCENE/NUS-SCENE-dataset/images/0199_434752251.jpg" \
- --model ResNet50_vd \
- --pretrained_model "./output_NUS-WIDE-SCENE/ResNet50_vd/best_model/ppcls" \
- --use_gpu True \
- --multilabel True \
- --class_num 33
+python3 python/predict_cls.py \
+ -c configs/inference_cls.yaml \
+ -o Global.infer_imgs=../dataset/CIFAR100/test/0/0001.png \
+ -o PostProcess.class_id_map_file=None
```
diff --git a/ppcls/configs/AlexNet/AlexNet.yaml b/ppcls/configs/AlexNet/AlexNet.yaml
deleted file mode 100644
index d1bf3f69b..000000000
--- a/ppcls/configs/AlexNet/AlexNet.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "AlexNet"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.01
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
diff --git a/ppcls/configs/DPN/DPN107.yaml b/ppcls/configs/DPN/DPN107.yaml
deleted file mode 100644
index f7e9dcaab..000000000
--- a/ppcls/configs/DPN/DPN107.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DPN107'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DPN/DPN131.yaml b/ppcls/configs/DPN/DPN131.yaml
deleted file mode 100644
index b07e57471..000000000
--- a/ppcls/configs/DPN/DPN131.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DPN131'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DPN/DPN68.yaml b/ppcls/configs/DPN/DPN68.yaml
deleted file mode 100644
index fc89a95ad..000000000
--- a/ppcls/configs/DPN/DPN68.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DPN68'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DPN/DPN92.yaml b/ppcls/configs/DPN/DPN92.yaml
deleted file mode 100644
index ff75eb546..000000000
--- a/ppcls/configs/DPN/DPN92.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DPN92'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DPN/DPN98.yaml b/ppcls/configs/DPN/DPN98.yaml
deleted file mode 100644
index 9fe706e75..000000000
--- a/ppcls/configs/DPN/DPN98.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DPN98'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DarkNet/DarkNet53.yaml b/ppcls/configs/DarkNet/DarkNet53.yaml
deleted file mode 100644
index cd6b82af3..000000000
--- a/ppcls/configs/DarkNet/DarkNet53.yaml
+++ /dev/null
@@ -1,77 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "DarkNet53"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 256, 256]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 256
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 256
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/DeiT/DeiT_base_distilled_patch16_224.yaml b/ppcls/configs/DeiT/DeiT_base_distilled_patch16_224.yaml
deleted file mode 100644
index e74df247f..000000000
--- a/ppcls/configs/DeiT/DeiT_base_distilled_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DeiT_base_distilled_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DeiT/DeiT_base_distilled_patch16_384.yaml b/ppcls/configs/DeiT/DeiT_base_distilled_patch16_384.yaml
deleted file mode 100644
index 75697e8aa..000000000
--- a/ppcls/configs/DeiT/DeiT_base_distilled_patch16_384.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DeiT_base_distilled_patch16_384'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 384
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 426
- - CropImage:
- size: 384
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DeiT/DeiT_base_patch16_224.yaml b/ppcls/configs/DeiT/DeiT_base_patch16_224.yaml
deleted file mode 100644
index 267b0a504..000000000
--- a/ppcls/configs/DeiT/DeiT_base_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DeiT_base_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DeiT/DeiT_base_patch16_384.yaml b/ppcls/configs/DeiT/DeiT_base_patch16_384.yaml
deleted file mode 100644
index f8dcc3cf5..000000000
--- a/ppcls/configs/DeiT/DeiT_base_patch16_384.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DeiT_base_patch16_384'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 384
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 426
- - CropImage:
- size: 384
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DeiT/DeiT_small_distilled_patch16_224.yaml b/ppcls/configs/DeiT/DeiT_small_distilled_patch16_224.yaml
deleted file mode 100644
index 992dab9a9..000000000
--- a/ppcls/configs/DeiT/DeiT_small_distilled_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DeiT_small_distilled_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DeiT/DeiT_small_patch16_224.yaml b/ppcls/configs/DeiT/DeiT_small_patch16_224.yaml
deleted file mode 100644
index ba7737429..000000000
--- a/ppcls/configs/DeiT/DeiT_small_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DeiT_small_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DeiT/DeiT_tiny_distilled_patch16_224.yaml b/ppcls/configs/DeiT/DeiT_tiny_distilled_patch16_224.yaml
deleted file mode 100644
index 5ddfbd596..000000000
--- a/ppcls/configs/DeiT/DeiT_tiny_distilled_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DeiT_tiny_distilled_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DeiT/DeiT_tiny_patch16_224.yaml b/ppcls/configs/DeiT/DeiT_tiny_patch16_224.yaml
deleted file mode 100644
index 1ce0b9712..000000000
--- a/ppcls/configs/DeiT/DeiT_tiny_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DeiT_tiny_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DenseNet/DenseNet121.yaml b/ppcls/configs/DenseNet/DenseNet121.yaml
deleted file mode 100644
index 59b5138c2..000000000
--- a/ppcls/configs/DenseNet/DenseNet121.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DenseNet121'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DenseNet/DenseNet161.yaml b/ppcls/configs/DenseNet/DenseNet161.yaml
deleted file mode 100644
index f96032c06..000000000
--- a/ppcls/configs/DenseNet/DenseNet161.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DenseNet161'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DenseNet/DenseNet169.yaml b/ppcls/configs/DenseNet/DenseNet169.yaml
deleted file mode 100644
index 2b49d97fc..000000000
--- a/ppcls/configs/DenseNet/DenseNet169.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DenseNet169'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DenseNet/DenseNet201.yaml b/ppcls/configs/DenseNet/DenseNet201.yaml
deleted file mode 100644
index 4e06bdca9..000000000
--- a/ppcls/configs/DenseNet/DenseNet201.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DenseNet201'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/DenseNet/DenseNet264.yaml b/ppcls/configs/DenseNet/DenseNet264.yaml
deleted file mode 100644
index b1ca63eb5..000000000
--- a/ppcls/configs/DenseNet/DenseNet264.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'DenseNet264'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/EfficientNet/EfficientNetB0.yaml b/ppcls/configs/EfficientNet/EfficientNetB0.yaml
deleted file mode 100644
index 97acaedca..000000000
--- a/ppcls/configs/EfficientNet/EfficientNetB0.yaml
+++ /dev/null
@@ -1,86 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "EfficientNetB0"
- params:
- padding_type : "SAME"
- override_params:
- drop_connect_rate: 0.1
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-use_ema: True
-ema_decay: 0.9999
-use_aa: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'ExponentialWarmup'
- params:
- lr: 0.032
-
-OPTIMIZER:
- function: 'RMSProp'
- params:
- momentum: 0.9
- rho: 0.9
- epsilon: 0.001
- regularizer:
- function: 'L2'
- factor: 0.00001
-
-TRAIN:
- batch_size: 512
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- interpolation: 2
- - RandFlipImage:
- flip_code: 1
- - AutoAugment:
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 128
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- interpolation: 2
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/GhostNet/GhostNet_x0_5.yaml b/ppcls/configs/GhostNet/GhostNet_x0_5.yaml
deleted file mode 100644
index d3bbcc4c4..000000000
--- a/ppcls/configs/GhostNet/GhostNet_x0_5.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'GhostNet_x0_5'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.8
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0000400
-
-TRAIN:
- batch_size: 2048
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/GhostNet/GhostNet_x1_0.yaml b/ppcls/configs/GhostNet/GhostNet_x1_0.yaml
deleted file mode 100644
index 76f565f1c..000000000
--- a/ppcls/configs/GhostNet/GhostNet_x1_0.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'GhostNet_x1_0'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.4
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0000400
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/GhostNet/GhostNet_x1_3.yaml b/ppcls/configs/GhostNet/GhostNet_x1_3.yaml
deleted file mode 100644
index 11118b9fb..000000000
--- a/ppcls/configs/GhostNet/GhostNet_x1_3.yaml
+++ /dev/null
@@ -1,73 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'GhostNet_x1_3'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.4
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0000400
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - AutoAugment:
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/HRNet/HRNet_W18_C.yaml b/ppcls/configs/HRNet/HRNet_W18_C.yaml
deleted file mode 100644
index cf0656cea..000000000
--- a/ppcls/configs/HRNet/HRNet_W18_C.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'HRNet_W18_C'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/HRNet/HRNet_W30_C.yaml b/ppcls/configs/HRNet/HRNet_W30_C.yaml
deleted file mode 100644
index 980b9c45e..000000000
--- a/ppcls/configs/HRNet/HRNet_W30_C.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'HRNet_W30_C'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/HRNet/HRNet_W32_C.yaml b/ppcls/configs/HRNet/HRNet_W32_C.yaml
deleted file mode 100644
index b2368eb32..000000000
--- a/ppcls/configs/HRNet/HRNet_W32_C.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'HRNet_W32_C'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/HRNet/HRNet_W40_C.yaml b/ppcls/configs/HRNet/HRNet_W40_C.yaml
deleted file mode 100644
index 86f7ff2b4..000000000
--- a/ppcls/configs/HRNet/HRNet_W40_C.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'HRNet_W40_C'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/HRNet/HRNet_W44_C.yaml b/ppcls/configs/HRNet/HRNet_W44_C.yaml
deleted file mode 100644
index 2b1649e89..000000000
--- a/ppcls/configs/HRNet/HRNet_W44_C.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'HRNet_W44_C'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/HRNet/HRNet_W48_C.yaml b/ppcls/configs/HRNet/HRNet_W48_C.yaml
deleted file mode 100644
index ba3e32e5b..000000000
--- a/ppcls/configs/HRNet/HRNet_W48_C.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'HRNet_W48_C'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/HRNet/HRNet_W64_C.yaml b/ppcls/configs/HRNet/HRNet_W64_C.yaml
deleted file mode 100644
index d8234bb04..000000000
--- a/ppcls/configs/HRNet/HRNet_W64_C.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'HRNet_W64_C'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Inception/GoogLeNet.yaml b/ppcls/configs/Inception/GoogLeNet.yaml
deleted file mode 100644
index 9fe093e22..000000000
--- a/ppcls/configs/Inception/GoogLeNet.yaml
+++ /dev/null
@@ -1,69 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "GoogLeNet"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Inception/InceptionV3.yaml b/ppcls/configs/Inception/InceptionV3.yaml
deleted file mode 100644
index 3f3e96c71..000000000
--- a/ppcls/configs/Inception/InceptionV3.yaml
+++ /dev/null
@@ -1,77 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'InceptionV3'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 299, 299]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 299
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-
-
-VALID:
- batch_size: 16
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 320
- - CropImage:
- size: 299
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Inception/InceptionV4.yaml b/ppcls/configs/Inception/InceptionV4.yaml
deleted file mode 100644
index 0f5d1cd45..000000000
--- a/ppcls/configs/Inception/InceptionV4.yaml
+++ /dev/null
@@ -1,77 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'InceptionV4'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 299, 299]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 299
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-
-
-VALID:
- batch_size: 16
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 320
- - CropImage:
- size: 299
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/MixNet/MixNet_L.yaml b/ppcls/configs/MixNet/MixNet_L.yaml
deleted file mode 100644
index 9ba412958..000000000
--- a/ppcls/configs/MixNet/MixNet_L.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-# just for finetune, the config for training on ImageNet is coming soon
-mode: 'train'
-ARCHITECTURE:
- name: 'MixNet_L'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/MixNet/MixNet_M.yaml b/ppcls/configs/MixNet/MixNet_M.yaml
deleted file mode 100644
index 359db3214..000000000
--- a/ppcls/configs/MixNet/MixNet_M.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-#just for finetune, the config for training on ImageNet is coming soon
-mode: 'train'
-ARCHITECTURE:
- name: 'MixNet_M'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/MixNet/MixNet_S.yaml b/ppcls/configs/MixNet/MixNet_S.yaml
deleted file mode 100644
index 9c961a0d7..000000000
--- a/ppcls/configs/MixNet/MixNet_S.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-# just for finetune, the config for training on ImageNet is coming soon.
-mode: 'train'
-ARCHITECTURE:
- name: 'MixNet_S'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/MobileNetV1/MobileNetV1.yaml b/ppcls/configs/MobileNetV1/MobileNetV1.yaml
deleted file mode 100644
index 6c2d3961d..000000000
--- a/ppcls/configs/MobileNetV1/MobileNetV1.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV1"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00003
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV1/MobileNetV1_x0_25.yaml b/ppcls/configs/MobileNetV1/MobileNetV1_x0_25.yaml
deleted file mode 100644
index 51af8ae86..000000000
--- a/ppcls/configs/MobileNetV1/MobileNetV1_x0_25.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV1_x0_25"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00003
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV1/MobileNetV1_x0_5.yaml b/ppcls/configs/MobileNetV1/MobileNetV1_x0_5.yaml
deleted file mode 100644
index ddc8f1b27..000000000
--- a/ppcls/configs/MobileNetV1/MobileNetV1_x0_5.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV1_x0_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00003
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV1/MobileNetV1_x0_75.yaml b/ppcls/configs/MobileNetV1/MobileNetV1_x0_75.yaml
deleted file mode 100644
index 13affb6e8..000000000
--- a/ppcls/configs/MobileNetV1/MobileNetV1_x0_75.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV1_x0_75"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00003
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV2/MobileNetV2.yaml b/ppcls/configs/MobileNetV2/MobileNetV2.yaml
deleted file mode 100644
index d7e059794..000000000
--- a/ppcls/configs/MobileNetV2/MobileNetV2.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV2"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00004
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV2/MobileNetV2_x0_25.yaml b/ppcls/configs/MobileNetV2/MobileNetV2_x0_25.yaml
deleted file mode 100644
index 626978c0c..000000000
--- a/ppcls/configs/MobileNetV2/MobileNetV2_x0_25.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV2_x0_25"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00003
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- ratio: [1.0, 1.0]
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV2/MobileNetV2_x0_5.yaml b/ppcls/configs/MobileNetV2/MobileNetV2_x0_5.yaml
deleted file mode 100644
index d8b8db02d..000000000
--- a/ppcls/configs/MobileNetV2/MobileNetV2_x0_5.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV2_x0_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00003
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- ratio: [1.0, 1.0]
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV2/MobileNetV2_x0_75.yaml b/ppcls/configs/MobileNetV2/MobileNetV2_x0_75.yaml
deleted file mode 100644
index 2830518ec..000000000
--- a/ppcls/configs/MobileNetV2/MobileNetV2_x0_75.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV2_x0_75"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00004
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV2/MobileNetV2_x1_5.yaml b/ppcls/configs/MobileNetV2/MobileNetV2_x1_5.yaml
deleted file mode 100644
index d091c3013..000000000
--- a/ppcls/configs/MobileNetV2/MobileNetV2_x1_5.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV2_x1_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00004
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV2/MobileNetV2_x2_0.yaml b/ppcls/configs/MobileNetV2/MobileNetV2_x2_0.yaml
deleted file mode 100644
index cd5df7d09..000000000
--- a/ppcls/configs/MobileNetV2/MobileNetV2_x2_0.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV2_x2_0"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00004
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_large_x0_35.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_large_x0_35.yaml
deleted file mode 100644
index 829f5375f..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_large_x0_35.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_large_x0_35"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 2.6
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00002
-
-TRAIN:
- batch_size: 4096
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_large_x0_5.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_large_x0_5.yaml
deleted file mode 100644
index 9dab3b875..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_large_x0_5.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_large_x0_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 1.3
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00002
-
-TRAIN:
- batch_size: 2048
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_large_x0_75.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_large_x0_75.yaml
deleted file mode 100644
index 124324d60..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_large_x0_75.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_large_x0_75"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 1.3
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00002
-
-TRAIN:
- batch_size: 2048
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_large_x1_0.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_large_x1_0.yaml
deleted file mode 100644
index 9c85f44fa..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_large_x1_0.yaml
+++ /dev/null
@@ -1,76 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_large_x1_0"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 1.3
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00002
-
-TRAIN:
- batch_size: 2048
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - AutoAugment:
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_large_x1_25.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_large_x1_25.yaml
deleted file mode 100644
index 3f5f48bbc..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_large_x1_25.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_large_x1_25"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.65
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00004
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_small_x0_35.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_small_x0_35.yaml
deleted file mode 100644
index ff5dcd714..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_small_x0_35.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_small_x0_35"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 2.6
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00001
-
-TRAIN:
- batch_size: 4096
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_small_x0_5.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_small_x0_5.yaml
deleted file mode 100644
index af0af7c10..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_small_x0_5.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_small_x0_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 2.6
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00001
-
-TRAIN:
- batch_size: 4096
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_small_x0_75.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_small_x0_75.yaml
deleted file mode 100644
index 4eae9a92a..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_small_x0_75.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_small_x0_75"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 2.6
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00002
-
-TRAIN:
- batch_size: 4096
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_small_x1_0.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_small_x1_0.yaml
deleted file mode 100644
index f63ce6d92..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_small_x1_0.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_small_x1_0"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 2.6
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00002
-
-TRAIN:
- batch_size: 4096
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/MobileNetV3/MobileNetV3_small_x1_25.yaml b/ppcls/configs/MobileNetV3/MobileNetV3_small_x1_25.yaml
deleted file mode 100644
index bc7b3193d..000000000
--- a/ppcls/configs/MobileNetV3/MobileNetV3_small_x1_25.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "MobileNetV3_small_x1_25"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 1.3
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00002
-
-TRAIN:
- batch_size: 2048
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/ReXNet/ReXNet_1_0.yaml b/ppcls/configs/ReXNet/ReXNet_1_0.yaml
deleted file mode 100644
index 9e168f8ac..000000000
--- a/ppcls/configs/ReXNet/ReXNet_1_0.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-# just for finetune, the config for training on ImageNet is coming soon
-mode: 'train'
-ARCHITECTURE:
- name: 'ReXNet_1_0'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ReXNet/ReXNet_1_3.yaml b/ppcls/configs/ReXNet/ReXNet_1_3.yaml
deleted file mode 100644
index 4a03f6784..000000000
--- a/ppcls/configs/ReXNet/ReXNet_1_3.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-# just for finetune, the config for training on ImageNet is coming soon
-mode: 'train'
-ARCHITECTURE:
- name: 'ReXNet_1_3'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ReXNet/ReXNet_1_5.yaml b/ppcls/configs/ReXNet/ReXNet_1_5.yaml
deleted file mode 100644
index 00923c3fe..000000000
--- a/ppcls/configs/ReXNet/ReXNet_1_5.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-# just for finetune, the config for training on ImageNet is coming soon
-mode: 'train'
-ARCHITECTURE:
- name: 'ReXNet_1_5'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ReXNet/ReXNet_2_0.yaml b/ppcls/configs/ReXNet/ReXNet_2_0.yaml
deleted file mode 100644
index 1a6b08bff..000000000
--- a/ppcls/configs/ReXNet/ReXNet_2_0.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-# just for finetune, the config for training on ImageNet is coming soon
-mode: 'train'
-ARCHITECTURE:
- name: 'ReXNet_2_0'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ReXNet/ReXNet_3_0.yaml b/ppcls/configs/ReXNet/ReXNet_3_0.yaml
deleted file mode 100644
index 18dbad1f1..000000000
--- a/ppcls/configs/ReXNet/ReXNet_3_0.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-# just for finetune, the config for training on ImageNet is coming soon
-mode: 'train'
-ARCHITECTURE:
- name: 'ReXNet_3_0'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RegNet/RegNetX_4GF.yaml b/ppcls/configs/RegNet/RegNetX_4GF.yaml
deleted file mode 100644
index fab32313f..000000000
--- a/ppcls/configs/RegNet/RegNetX_4GF.yaml
+++ /dev/null
@@ -1,73 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RegNetX_4GF'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 100
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.4
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000050
-
-TRAIN:
- batch_size: 512
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_A0.yaml b/ppcls/configs/RepVGG/RepVGG_A0.yaml
deleted file mode 100644
index a8ff9972e..000000000
--- a/ppcls/configs/RepVGG/RepVGG_A0.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_A0'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_A1.yaml b/ppcls/configs/RepVGG/RepVGG_A1.yaml
deleted file mode 100644
index d755da455..000000000
--- a/ppcls/configs/RepVGG/RepVGG_A1.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_A1'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_A2.yaml b/ppcls/configs/RepVGG/RepVGG_A2.yaml
deleted file mode 100644
index 44e4e49be..000000000
--- a/ppcls/configs/RepVGG/RepVGG_A2.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_A2'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B0.yaml b/ppcls/configs/RepVGG/RepVGG_B0.yaml
deleted file mode 100644
index be47f0d77..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B0.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B0'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B1.yaml b/ppcls/configs/RepVGG/RepVGG_B1.yaml
deleted file mode 100644
index 62694e41d..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B1.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B1'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B1g2.yaml b/ppcls/configs/RepVGG/RepVGG_B1g2.yaml
deleted file mode 100644
index 3251b0464..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B1g2.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B1g2'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B1g4.yaml b/ppcls/configs/RepVGG/RepVGG_B1g4.yaml
deleted file mode 100644
index 5441d4e4b..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B1g4.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B1g4'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B2.yaml b/ppcls/configs/RepVGG/RepVGG_B2.yaml
deleted file mode 100644
index 60da46b9e..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B2.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B2'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B2g2.yaml b/ppcls/configs/RepVGG/RepVGG_B2g2.yaml
deleted file mode 100644
index 09ff2d5bf..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B2g2.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B2g2'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B2g4.yaml b/ppcls/configs/RepVGG/RepVGG_B2g4.yaml
deleted file mode 100644
index 146917a37..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B2g4.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B2g4'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B3.yaml b/ppcls/configs/RepVGG/RepVGG_B3.yaml
deleted file mode 100644
index 765b38bea..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B3.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B3'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B3g2.yaml b/ppcls/configs/RepVGG/RepVGG_B3g2.yaml
deleted file mode 100644
index 09a8ee573..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B3g2.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B3g2'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/RepVGG/RepVGG_B3g4.yaml b/ppcls/configs/RepVGG/RepVGG_B3g4.yaml
deleted file mode 100644
index c5adcfe11..000000000
--- a/ppcls/configs/RepVGG/RepVGG_B3g4.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'RepVGG_B3g4'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Res2Net/Res2Net101_vd_26w_4s.yaml b/ppcls/configs/Res2Net/Res2Net101_vd_26w_4s.yaml
deleted file mode 100644
index abc4213ac..000000000
--- a/ppcls/configs/Res2Net/Res2Net101_vd_26w_4s.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Res2Net101_vd_26w_4s'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Res2Net/Res2Net200_vd_26w_4s.yaml b/ppcls/configs/Res2Net/Res2Net200_vd_26w_4s.yaml
deleted file mode 100644
index bdc4889b2..000000000
--- a/ppcls/configs/Res2Net/Res2Net200_vd_26w_4s.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Res2Net200_vd_26w_4s'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Res2Net/Res2Net50_14w_8s.yaml b/ppcls/configs/Res2Net/Res2Net50_14w_8s.yaml
deleted file mode 100644
index 4f61ab1d5..000000000
--- a/ppcls/configs/Res2Net/Res2Net50_14w_8s.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Res2Net50_14w_8s'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Res2Net/Res2Net50_26w_4s.yaml b/ppcls/configs/Res2Net/Res2Net50_26w_4s.yaml
deleted file mode 100644
index 8aeac8e0b..000000000
--- a/ppcls/configs/Res2Net/Res2Net50_26w_4s.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Res2Net50_26w_4s'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Res2Net/Res2Net50_vd_26w_4s.yaml b/ppcls/configs/Res2Net/Res2Net50_vd_26w_4s.yaml
deleted file mode 100644
index ef39fa2f3..000000000
--- a/ppcls/configs/Res2Net/Res2Net50_vd_26w_4s.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Res2Net50_vd_26w_4s'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeSt/ResNeSt101.yaml b/ppcls/configs/ResNeSt/ResNeSt101.yaml
deleted file mode 100644
index 2f07083ba..000000000
--- a/ppcls/configs/ResNeSt/ResNeSt101.yaml
+++ /dev/null
@@ -1,76 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeSt101'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 256, 256]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000070
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 256
- - RandFlipImage:
- flip_code: 1
- - AutoAugment:
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - CutmixOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 288
- - CropImage:
- size: 256
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeSt/ResNeSt50.yaml b/ppcls/configs/ResNeSt/ResNeSt50.yaml
deleted file mode 100644
index e91f99dbf..000000000
--- a/ppcls/configs/ResNeSt/ResNeSt50.yaml
+++ /dev/null
@@ -1,76 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeSt50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000070
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - AutoAugment:
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - CutmixOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeSt/ResNeSt50_fast_1s1x64d.yaml b/ppcls/configs/ResNeSt/ResNeSt50_fast_1s1x64d.yaml
deleted file mode 100644
index 0d4fffe2d..000000000
--- a/ppcls/configs/ResNeSt/ResNeSt50_fast_1s1x64d.yaml
+++ /dev/null
@@ -1,76 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeSt50_fast_1s1x64d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000070
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - AutoAugment:
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - CutmixOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt101_32x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt101_32x4d.yaml
deleted file mode 100644
index 009f14dfa..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt101_32x4d.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt101_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt101_32x4d_fp16.yaml b/ppcls/configs/ResNeXt/ResNeXt101_32x4d_fp16.yaml
deleted file mode 100644
index 570d725a1..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt101_32x4d_fp16.yaml
+++ /dev/null
@@ -1,89 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt101_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [4, 224, 224]
-
-use_dali: True
-use_gpu: True
-data_format: "NCHW"
-image_channel: &image_channel 4
-image_shape: [*image_channel, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-# mixed precision training
-AMP:
- scale_loss: 128.0
- use_dynamic_loss_scaling: True
- use_pure_fp16: &use_pure_fp16 True
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- multi_precision: *use_pure_fp16
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- output_fp16: *use_pure_fp16
- channel_num: *image_channel
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt101_64x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt101_64x4d.yaml
deleted file mode 100644
index 0f2c6251e..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt101_64x4d.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt101_64x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000150
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt101_vd_32x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt101_vd_32x4d.yaml
deleted file mode 100644
index e78a241ee..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt101_vd_32x4d.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt101_vd_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt101_vd_64x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt101_vd_64x4d.yaml
deleted file mode 100644
index 429458056..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt101_vd_64x4d.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt101_vd_64x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt152_32x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt152_32x4d.yaml
deleted file mode 100644
index e656dc77a..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt152_32x4d.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt152_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt152_64x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt152_64x4d.yaml
deleted file mode 100644
index 813201e95..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt152_64x4d.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt152_64x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000180
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt152_vd_32x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt152_vd_32x4d.yaml
deleted file mode 100644
index ed9b6da15..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt152_vd_32x4d.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt152_vd_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt152_vd_64x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt152_vd_64x4d.yaml
deleted file mode 100644
index 1d234f7bf..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt152_vd_64x4d.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt152_vd_64x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt50_32x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt50_32x4d.yaml
deleted file mode 100644
index 312a314f5..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt50_32x4d.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt50_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt/ResNeXt50_64x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt50_64x4d.yaml
deleted file mode 100644
index 66a6216cb..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt50_64x4d.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "ResNeXt50_64x4d"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
-
-TRAIN:
- batch_size: 32
- num_workers: 8
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/ResNeXt/ResNeXt50_vd_32x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt50_vd_32x4d.yaml
deleted file mode 100644
index 8f7f8a20f..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt50_vd_32x4d.yaml
+++ /dev/null
@@ -1,80 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "ResNeXt50_vd_32x4d"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/ResNeXt/ResNeXt50_vd_64x4d.yaml b/ppcls/configs/ResNeXt/ResNeXt50_vd_64x4d.yaml
deleted file mode 100644
index 29b1195c0..000000000
--- a/ppcls/configs/ResNeXt/ResNeXt50_vd_64x4d.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNeXt50_vd_64x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNeXt101_wsl/ResNeXt101_32x8d_wsl.yaml b/ppcls/configs/ResNeXt101_wsl/ResNeXt101_32x8d_wsl.yaml
deleted file mode 100644
index 69485ba19..000000000
--- a/ppcls/configs/ResNeXt101_wsl/ResNeXt101_32x8d_wsl.yaml
+++ /dev/null
@@ -1,35 +0,0 @@
-mode: 'valid'
-ARCHITECTURE:
- name: 'ResNeXt101_32x8d_wsl'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 224
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet101.yaml b/ppcls/configs/ResNet/ResNet101.yaml
deleted file mode 100644
index 039c40a66..000000000
--- a/ppcls/configs/ResNet/ResNet101.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet101'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet101_vd.yaml b/ppcls/configs/ResNet/ResNet101_vd.yaml
deleted file mode 100644
index 30c7ad147..000000000
--- a/ppcls/configs/ResNet/ResNet101_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet101_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet152.yaml b/ppcls/configs/ResNet/ResNet152.yaml
deleted file mode 100644
index 3575fa74f..000000000
--- a/ppcls/configs/ResNet/ResNet152.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet152'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet152_vd.yaml b/ppcls/configs/ResNet/ResNet152_vd.yaml
deleted file mode 100644
index d1f2e46a8..000000000
--- a/ppcls/configs/ResNet/ResNet152_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet152_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet18.yaml b/ppcls/configs/ResNet/ResNet18.yaml
deleted file mode 100644
index b97183ed8..000000000
--- a/ppcls/configs/ResNet/ResNet18.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet18'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet18_vd.yaml b/ppcls/configs/ResNet/ResNet18_vd.yaml
deleted file mode 100644
index edb89ca52..000000000
--- a/ppcls/configs/ResNet/ResNet18_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet18_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000070
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet200_vd.yaml b/ppcls/configs/ResNet/ResNet200_vd.yaml
deleted file mode 100644
index fa7fb83a5..000000000
--- a/ppcls/configs/ResNet/ResNet200_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet200_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet34.yaml b/ppcls/configs/ResNet/ResNet34.yaml
deleted file mode 100644
index 921a1a3c9..000000000
--- a/ppcls/configs/ResNet/ResNet34.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet34'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet34_vd.yaml b/ppcls/configs/ResNet/ResNet34_vd.yaml
deleted file mode 100644
index 6423e0c1a..000000000
--- a/ppcls/configs/ResNet/ResNet34_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet34_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000070
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet50.yaml b/ppcls/configs/ResNet/ResNet50.yaml
deleted file mode 100644
index 9c10e68dd..000000000
--- a/ppcls/configs/ResNet/ResNet50.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet50_fp16.yaml b/ppcls/configs/ResNet/ResNet50_fp16.yaml
deleted file mode 100644
index 992020931..000000000
--- a/ppcls/configs/ResNet/ResNet50_fp16.yaml
+++ /dev/null
@@ -1,89 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-is_distributed: True
-
-use_dali: True
-use_gpu: True
-data_format: "NHWC"
-image_channel: &image_channel 4
-image_shape: [*image_channel, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-# mixed precision training
-AMP:
- scale_loss: 128.0
- use_dynamic_loss_scaling: True
- use_pure_fp16: &use_pure_fp16 True
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- multi_precision: *use_pure_fp16
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- output_fp16: *use_pure_fp16
- channel_num: *image_channel
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet50_vc.yaml b/ppcls/configs/ResNet/ResNet50_vc.yaml
deleted file mode 100644
index 4decb128d..000000000
--- a/ppcls/configs/ResNet/ResNet50_vc.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vc'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ResNet/ResNet50_vd.yaml b/ppcls/configs/ResNet/ResNet50_vd.yaml
deleted file mode 100644
index 176aa5fa5..000000000
--- a/ppcls/configs/ResNet/ResNet50_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000070
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SENet/SENet154_vd.yaml b/ppcls/configs/SENet/SENet154_vd.yaml
deleted file mode 100644
index f67d83edf..000000000
--- a/ppcls/configs/SENet/SENet154_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SENet154_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SENet/SE_ResNeXt101_32x4d.yaml b/ppcls/configs/SENet/SE_ResNeXt101_32x4d.yaml
deleted file mode 100644
index 9b3371f37..000000000
--- a/ppcls/configs/SENet/SE_ResNeXt101_32x4d.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SE_ResNeXt101_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000015
-
-TRAIN:
- batch_size: 400
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SENet/SE_ResNeXt101_32x4d_fp16.yaml b/ppcls/configs/SENet/SE_ResNeXt101_32x4d_fp16.yaml
deleted file mode 100644
index ecd5d7912..000000000
--- a/ppcls/configs/SENet/SE_ResNeXt101_32x4d_fp16.yaml
+++ /dev/null
@@ -1,89 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SE_ResNeXt101_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-is_distributed: False
-
-use_dali: False
-use_gpu: True
-data_format: "NCHW"
-image_channel: &image_channel 4
-image_shape: [*image_channel, 224, 224]
-
-
-use_mix: False
-ls_epsilon: -1
-
-AMP:
- scale_loss: 128.0
- use_dynamic_loss_scaling: True
- use_pure_fp16: &use_pure_fp16 True
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- multi_precision: *use_pure_fp16
- regularizer:
- function: 'L2'
- factor: 0.000015
-
-TRAIN:
- batch_size: 96
- num_workers: 0
- file_list: "/home/datasets/ILSVRC2012/train_list.txt"
- data_dir: "/home/datasets/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- to_np: False
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- output_fp16: *use_pure_fp16
- channel_num: *image_channel
- - ToCHWImage:
-
-VALID:
- batch_size: 16
- num_workers: 0
- file_list: "/home/datasets/ILSVRC2012/val_list.txt"
- data_dir: "/home/datasets/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- to_np: False
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SENet/SE_ResNeXt50_32x4d.yaml b/ppcls/configs/SENet/SE_ResNeXt50_32x4d.yaml
deleted file mode 100644
index 64dff2ef8..000000000
--- a/ppcls/configs/SENet/SE_ResNeXt50_32x4d.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SE_ResNeXt50_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000120
-
-TRAIN:
- batch_size: 400
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SENet/SE_ResNeXt50_vd_32x4d.yaml b/ppcls/configs/SENet/SE_ResNeXt50_vd_32x4d.yaml
deleted file mode 100644
index d25616ad6..000000000
--- a/ppcls/configs/SENet/SE_ResNeXt50_vd_32x4d.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SE_ResNeXt50_vd_32x4d'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SENet/SE_ResNet18_vd.yaml b/ppcls/configs/SENet/SE_ResNet18_vd.yaml
deleted file mode 100644
index 51520d678..000000000
--- a/ppcls/configs/SENet/SE_ResNet18_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SE_ResNet18_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000070
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SENet/SE_ResNet34_vd.yaml b/ppcls/configs/SENet/SE_ResNet34_vd.yaml
deleted file mode 100644
index f0ec42701..000000000
--- a/ppcls/configs/SENet/SE_ResNet34_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SE_ResNet34_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000070
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SENet/SE_ResNet50_vd.yaml b/ppcls/configs/SENet/SE_ResNet50_vd.yaml
deleted file mode 100644
index b19270c89..000000000
--- a/ppcls/configs/SENet/SE_ResNet50_vd.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SE_ResNet50_vd'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/ShuffleNet/ShuffleNetV2_swish.yaml b/ppcls/configs/ShuffleNet/ShuffleNetV2_swish.yaml
deleted file mode 100644
index e9e9e7fed..000000000
--- a/ppcls/configs/ShuffleNet/ShuffleNetV2_swish.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "ShuffleNetV2_swish"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.5
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00004
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/ShuffleNet/ShuffleNetV2_x0_25.yaml b/ppcls/configs/ShuffleNet/ShuffleNetV2_x0_25.yaml
deleted file mode 100644
index d8495dca8..000000000
--- a/ppcls/configs/ShuffleNet/ShuffleNetV2_x0_25.yaml
+++ /dev/null
@@ -1,76 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "ShuffleNetV2_x0_25"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.5
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00003
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- scale: [0.64, 1.0]
- ratio: [0.8, 1.2]
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/ShuffleNet/ShuffleNetV2_x0_33.yaml b/ppcls/configs/ShuffleNet/ShuffleNetV2_x0_33.yaml
deleted file mode 100644
index e10e900e3..000000000
--- a/ppcls/configs/ShuffleNet/ShuffleNetV2_x0_33.yaml
+++ /dev/null
@@ -1,76 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "ShuffleNetV2_x0_33"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.5
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00003
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- scale: [0.64, 1.0]
- ratio: [0.8, 1.2]
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/ShuffleNet/ShuffleNetV2_x0_5.yaml b/ppcls/configs/ShuffleNet/ShuffleNetV2_x0_5.yaml
deleted file mode 100644
index ba6f5ff4e..000000000
--- a/ppcls/configs/ShuffleNet/ShuffleNetV2_x0_5.yaml
+++ /dev/null
@@ -1,76 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "ShuffleNetV2_x0_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.5
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00003
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- scale: [0.64, 1.0]
- ratio: [0.8, 1.2]
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/ShuffleNet/ShuffleNetV2_x1_0.yaml b/ppcls/configs/ShuffleNet/ShuffleNetV2_x1_0.yaml
deleted file mode 100644
index 404550cef..000000000
--- a/ppcls/configs/ShuffleNet/ShuffleNetV2_x1_0.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "ShuffleNetV2_x1_0"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.5
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00004
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/ShuffleNet/ShuffleNetV2_x1_5.yaml b/ppcls/configs/ShuffleNet/ShuffleNetV2_x1_5.yaml
deleted file mode 100644
index 7570afc6f..000000000
--- a/ppcls/configs/ShuffleNet/ShuffleNetV2_x1_5.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "ShuffleNetV2_x1_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.25
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00004
-
-TRAIN:
- batch_size: 512
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- ratio: [1.0, 1.0]
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/ShuffleNet/ShuffleNetV2_x2_0.yaml b/ppcls/configs/ShuffleNet/ShuffleNetV2_x2_0.yaml
deleted file mode 100644
index b54063ae7..000000000
--- a/ppcls/configs/ShuffleNet/ShuffleNetV2_x2_0.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "ShuffleNetV2_x2_0"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.25
- warmup_epoch: 5
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00004
-
-TRAIN:
- batch_size: 512
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/SqueezeNet/SqueezeNet1_0.yaml b/ppcls/configs/SqueezeNet/SqueezeNet1_0.yaml
deleted file mode 100644
index 6824a59ac..000000000
--- a/ppcls/configs/SqueezeNet/SqueezeNet1_0.yaml
+++ /dev/null
@@ -1,71 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "SqueezeNet1_0"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'CosineWarmup'
- params:
- lr: 0.02
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
diff --git a/ppcls/configs/SqueezeNet/SqueezeNet1_1.yaml b/ppcls/configs/SqueezeNet/SqueezeNet1_1.yaml
deleted file mode 100644
index 73a456146..000000000
--- a/ppcls/configs/SqueezeNet/SqueezeNet1_1.yaml
+++ /dev/null
@@ -1,69 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "SqueezeNet1_1"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.02
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SwinTransformer/SwinTransformer_base_patch4_window12_384.yaml b/ppcls/configs/SwinTransformer/SwinTransformer_base_patch4_window12_384.yaml
deleted file mode 100644
index 815bce71b..000000000
--- a/ppcls/configs/SwinTransformer/SwinTransformer_base_patch4_window12_384.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SwinTransformer_base_patch4_window12_384'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- size: [384, 384]
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SwinTransformer/SwinTransformer_base_patch4_window7_224.yaml b/ppcls/configs/SwinTransformer/SwinTransformer_base_patch4_window7_224.yaml
deleted file mode 100644
index eccc77630..000000000
--- a/ppcls/configs/SwinTransformer/SwinTransformer_base_patch4_window7_224.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SwinTransformer_base_patch4_window7_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SwinTransformer/SwinTransformer_large_patch4_window12_384.yaml b/ppcls/configs/SwinTransformer/SwinTransformer_large_patch4_window12_384.yaml
deleted file mode 100644
index 4d05754d1..000000000
--- a/ppcls/configs/SwinTransformer/SwinTransformer_large_patch4_window12_384.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SwinTransformer_large_patch4_window12_384'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 128
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- size: [384, 384]
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SwinTransformer/SwinTransformer_large_patch4_window7_224.yaml b/ppcls/configs/SwinTransformer/SwinTransformer_large_patch4_window7_224.yaml
deleted file mode 100644
index f2481da11..000000000
--- a/ppcls/configs/SwinTransformer/SwinTransformer_large_patch4_window7_224.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SwinTransformer_large_patch4_window7_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SwinTransformer/SwinTransformer_small_patch4_window7_224.yaml b/ppcls/configs/SwinTransformer/SwinTransformer_small_patch4_window7_224.yaml
deleted file mode 100644
index 4f724b7f0..000000000
--- a/ppcls/configs/SwinTransformer/SwinTransformer_small_patch4_window7_224.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SwinTransformer_small_patch4_window7_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/SwinTransformer/SwinTransformer_tiny_patch4_window7_224.yaml b/ppcls/configs/SwinTransformer/SwinTransformer_tiny_patch4_window7_224.yaml
deleted file mode 100644
index 59c9038ed..000000000
--- a/ppcls/configs/SwinTransformer/SwinTransformer_tiny_patch4_window7_224.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'SwinTransformer_tiny_patch4_window7_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Piecewise'
- params:
- lr: 0.1
- decay_epochs: [30, 60, 90]
- gamma: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/VGG/VGG11.yaml b/ppcls/configs/VGG/VGG11.yaml
deleted file mode 100644
index ad5c2f6f1..000000000
--- a/ppcls/configs/VGG/VGG11.yaml
+++ /dev/null
@@ -1,69 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "VGG11"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 90
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.1
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0002
-
-TRAIN:
- batch_size: 512
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/VGG/VGG13.yaml b/ppcls/configs/VGG/VGG13.yaml
deleted file mode 100644
index 347cb0b7e..000000000
--- a/ppcls/configs/VGG/VGG13.yaml
+++ /dev/null
@@ -1,70 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "VGG13"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 90
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0003
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
diff --git a/ppcls/configs/VGG/VGG16.yaml b/ppcls/configs/VGG/VGG16.yaml
deleted file mode 100644
index 75431ffc1..000000000
--- a/ppcls/configs/VGG/VGG16.yaml
+++ /dev/null
@@ -1,70 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "VGG16"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 90
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0004
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
diff --git a/ppcls/configs/VGG/VGG19.yaml b/ppcls/configs/VGG/VGG19.yaml
deleted file mode 100644
index b591bc08e..000000000
--- a/ppcls/configs/VGG/VGG19.yaml
+++ /dev/null
@@ -1,70 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: "VGG19"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 150
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0004
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
diff --git a/ppcls/configs/VisionTransformer/ViT_base_patch16_224.yaml b/ppcls/configs/VisionTransformer/ViT_base_patch16_224.yaml
deleted file mode 100644
index 80f1f1ab0..000000000
--- a/ppcls/configs/VisionTransformer/ViT_base_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ViT_base_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.005
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 48
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 48
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/VisionTransformer/ViT_base_patch16_384.yaml b/ppcls/configs/VisionTransformer/ViT_base_patch16_384.yaml
deleted file mode 100644
index 4b8a99822..000000000
--- a/ppcls/configs/VisionTransformer/ViT_base_patch16_384.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ViT_base_patch16_384'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.005
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 48
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 384
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 48
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 384
- - CropImage:
- size: 384
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/VisionTransformer/ViT_base_patch32_384.yaml b/ppcls/configs/VisionTransformer/ViT_base_patch32_384.yaml
deleted file mode 100644
index 4eddb0ac9..000000000
--- a/ppcls/configs/VisionTransformer/ViT_base_patch32_384.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ViT_base_patch32_384'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.005
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 48
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 384
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 48
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 384
- - CropImage:
- size: 384
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
\ No newline at end of file
diff --git a/ppcls/configs/VisionTransformer/ViT_huge_patch16_224.yaml b/ppcls/configs/VisionTransformer/ViT_huge_patch16_224.yaml
deleted file mode 100644
index f2841a5e2..000000000
--- a/ppcls/configs/VisionTransformer/ViT_huge_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ViT_huge_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 16
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 16
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/VisionTransformer/ViT_huge_patch32_384.yaml b/ppcls/configs/VisionTransformer/ViT_huge_patch32_384.yaml
deleted file mode 100644
index 3859d132d..000000000
--- a/ppcls/configs/VisionTransformer/ViT_huge_patch32_384.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ViT_huge_patch32_384'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.001
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 16
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 384
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 16
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 384
- - CropImage:
- size: 384
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/VisionTransformer/ViT_large_patch16_224.yaml b/ppcls/configs/VisionTransformer/ViT_large_patch16_224.yaml
deleted file mode 100644
index 55a5fdbd6..000000000
--- a/ppcls/configs/VisionTransformer/ViT_large_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ViT_large_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.003
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 32
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 32
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/VisionTransformer/ViT_large_patch16_384.yaml b/ppcls/configs/VisionTransformer/ViT_large_patch16_384.yaml
deleted file mode 100644
index b5e285aca..000000000
--- a/ppcls/configs/VisionTransformer/ViT_large_patch16_384.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ViT_large_patch16_384'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.003
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 32
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 384
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 32
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 384
- - CropImage:
- size: 384
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/VisionTransformer/ViT_large_patch32_384.yaml b/ppcls/configs/VisionTransformer/ViT_large_patch32_384.yaml
deleted file mode 100644
index 5a975656f..000000000
--- a/ppcls/configs/VisionTransformer/ViT_large_patch32_384.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ViT_large_patch32_384'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.003
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 32
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 384
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 32
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 384
- - CropImage:
- size: 384
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.5, 0.5, 0.5]
- std: [0.5, 0.5, 0.5]
- order: ''
- - ToCHWImage:
\ No newline at end of file
diff --git a/ppcls/configs/VisionTransformer/ViT_small_patch16_224.yaml b/ppcls/configs/VisionTransformer/ViT_small_patch16_224.yaml
deleted file mode 100644
index 702069ec0..000000000
--- a/ppcls/configs/VisionTransformer/ViT_small_patch16_224.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ViT_small_patch16_224'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.01
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000100
-
-TRAIN:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Xception/Xception41.yaml b/ppcls/configs/Xception/Xception41.yaml
deleted file mode 100644
index 4fbf30d53..000000000
--- a/ppcls/configs/Xception/Xception41.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Xception41'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 299, 299]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 299
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 320
- - CropImage:
- size: 299
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Xception/Xception41_deeplab.yaml b/ppcls/configs/Xception/Xception41_deeplab.yaml
deleted file mode 100644
index b94c2d0c7..000000000
--- a/ppcls/configs/Xception/Xception41_deeplab.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Xception41_deeplab'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 299, 299]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 299
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 320
- - CropImage:
- size: 299
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Xception/Xception65.yaml b/ppcls/configs/Xception/Xception65.yaml
deleted file mode 100644
index 6eb627a34..000000000
--- a/ppcls/configs/Xception/Xception65.yaml
+++ /dev/null
@@ -1,77 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Xception65'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 299, 299]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 299
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-
-
-VALID:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 320
- - CropImage:
- size: 299
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Xception/Xception65_deeplab.yaml b/ppcls/configs/Xception/Xception65_deeplab.yaml
deleted file mode 100644
index f112887a0..000000000
--- a/ppcls/configs/Xception/Xception65_deeplab.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Xception65_deeplab'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 299, 299]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.045
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 299
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-
-
-VALID:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 320
- - CropImage:
- size: 299
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/Xception/Xception71.yaml b/ppcls/configs/Xception/Xception71.yaml
deleted file mode 100644
index 60729a2aa..000000000
--- a/ppcls/configs/Xception/Xception71.yaml
+++ /dev/null
@@ -1,77 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'Xception71'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 299, 299]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.0225
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00010
-
-TRAIN:
- batch_size: 128
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/train_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 299
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-
-
-VALID:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/ILSVRC2012/val_list.txt"
- data_dir: "./dataset/ILSVRC2012/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 320
- - CropImage:
- size: 299
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml b/ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml
new file mode 100644
index 000000000..a102a9d0a
--- /dev/null
+++ b/ppcls/configs/quick_start/MobileNetV3_large_x1_0.yaml
@@ -0,0 +1,131 @@
+# global configs
+Global:
+ checkpoints: null
+ pretrained_model: null
+ output_dir: ./output/
+ device: gpu
+ class_num: 102
+ save_interval: 1
+ eval_during_train: True
+ eval_interval: 1
+ epochs: 20
+ print_batch_step: 10
+ use_visualdl: False
+ # used for static mode and model export
+ image_shape: [3, 224, 224]
+ save_inference_dir: ./inference
+
+# model architecture
+Arch:
+ name: MobileNetV3_large_x1_0
+
+# loss function config for traing/eval process
+Loss:
+ Train:
+ - CELoss:
+ weight: 1.0
+ Eval:
+ - CELoss:
+ weight: 1.0
+
+
+Optimizer:
+ name: Momentum
+ momentum: 0.9
+ lr:
+ name: Cosine
+ learning_rate: 0.00375
+ warmup_epoch: 5
+ last_epoch: -1
+ regularizer:
+ name: 'L2'
+ coeff: 0.000001
+
+
+# data loader for train and eval
+DataLoader:
+ Train:
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/flowers102/
+ cls_label_path: ./dataset/flowers102/train_list.txt
+ transform_ops:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - RandCropImage:
+ size: 224
+ - RandFlipImage:
+ flip_code: 1
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 32
+ drop_last: False
+ shuffle: True
+ loader:
+ num_workers: 4
+ use_shared_memory: True
+
+ Eval:
+ # TOTO: modify to the latest trainer
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/flowers102/
+ cls_label_path: ./dataset/flowers102/val_list.txt
+ transform_ops:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 256
+ - CropImage:
+ size: 224
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: False
+ loader:
+ num_workers: 4
+ use_shared_memory: True
+
+Infer:
+ infer_imgs: docs/images/whl/demo.jpg
+ batch_size: 10
+ transforms:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 256
+ - CropImage:
+ size: 224
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ - ToCHWImage:
+ PostProcess:
+ name: Topk
+ topk: 5
+ class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+ Train:
+ - TopkAcc:
+ topk: [1, 5]
+ Eval:
+ - TopkAcc:
+ topk: [1, 5]
diff --git a/ppcls/configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml b/ppcls/configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml
deleted file mode 100644
index f8dead622..000000000
--- a/ppcls/configs/quick_start/MobileNetV3_large_x1_0_finetune.yaml
+++ /dev/null
@@ -1,69 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'MobileNetV3_large_x1_0'
-pretrained_model: "./pretrained/MobileNetV3_large_x1_0_pretrained"
-model_save_dir: "./output/"
-use_gpu: True
-classes_num: 102
-total_images: 1020
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 20
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.00375
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000001
-
-TRAIN:
- batch_size: 32
- num_workers: 0
- file_list: "./dataset/flowers102/train_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 20
- num_workers: 0
- file_list: "./dataset/flowers102/val_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/quick_start/R50_vd_distill_MV3_large_x1_0.yaml b/ppcls/configs/quick_start/R50_vd_distill_MV3_large_x1_0.yaml
deleted file mode 100644
index c17b1f65c..000000000
--- a/ppcls/configs/quick_start/R50_vd_distill_MV3_large_x1_0.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd_distill_MobileNetV3_large_x1_0'
-
-pretrained_model:
- - "./pretrained/flowers102_R50_vd_final/ppcls"
- - "./pretrained/MobileNetV3_large_x1_0_pretrained"
-model_save_dir: "./output/"
-use_gpu: True
-classes_num: 102
-total_images: 7169
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 20
-topk: 5
-image_shape: [3, 224, 224]
-
-use_distillation: True
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.0125
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00007
-
-TRAIN:
- batch_size: 32
- num_workers: 0
- file_list: "./dataset/flowers102/train_extra_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 20
- num_workers: 0
- file_list: "./dataset/flowers102/val_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/quick_start/ResNet50_vd.yaml b/ppcls/configs/quick_start/ResNet50_vd.yaml
index 6ad57067f..f155f0f98 100644
--- a/ppcls/configs/quick_start/ResNet50_vd.yaml
+++ b/ppcls/configs/quick_start/ResNet50_vd.yaml
@@ -1,40 +1,54 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
+# global configs
+Global:
+ checkpoints: null
+ pretrained_model: null
+ output_dir: ./output/
+ device: gpu
+ class_num: 102
+ save_interval: 1
+ eval_during_train: True
+ eval_interval: 1
+ epochs: 20
+ print_batch_step: 10
+ use_visualdl: False
+ # used for static mode and model export
+ image_shape: [3, 224, 224]
+ save_inference_dir: ./inference
-checkpoints: ""
-pretrained_model: ""
-use_gpu: True
-model_save_dir: "./output/"
-classes_num: 102
-total_images: 1020
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 20
-topk: 5
-image_shape: [3, 224, 224]
+# model architecture
+Arch:
+ name: ResNet50_vd
+
+# loss function config for traing/eval process
+Loss:
+ Train:
+ - CELoss:
+ weight: 1.0
+ Eval:
+ - CELoss:
+ weight: 1.0
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.0125
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00001
+Optimizer:
+ name: Momentum
+ momentum: 0.9
+ lr:
+ name: Cosine
+ learning_rate: 0.0125
+ warmup_epoch: 5
+ regularizer:
+ name: 'L2'
+ coeff: 0.00001
-TRAIN:
- batch_size: 32
- num_workers: 0
- file_list: "./dataset/flowers102/train_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
+
+# data loader for train and eval
+DataLoader:
+ Train:
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/flowers102/
+ cls_label_path: ./dataset/flowers102/train_list.txt
+ transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
@@ -43,19 +57,27 @@ TRAIN:
- RandFlipImage:
flip_code: 1
- NormalizeImage:
- scale: 1./255.
+ scale: 1.0/255.0
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- - ToCHWImage:
-VALID:
- batch_size: 20
- num_workers: 0
- file_list: "./dataset/flowers102/val_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 32
+ drop_last: False
+ shuffle: True
+ loader:
+ num_workers: 4
+ use_shared_memory: True
+
+ Eval:
+ # TOTO: modify to the latest trainer
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/flowers102/
+ cls_label_path: ./dataset/flowers102/val_list.txt
+ transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
@@ -68,4 +90,41 @@ VALID:
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- - ToCHWImage:
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: False
+ loader:
+ num_workers: 4
+ use_shared_memory: True
+
+Infer:
+ infer_imgs: docs/images/whl/demo.jpg
+ batch_size: 10
+ transforms:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 256
+ - CropImage:
+ size: 224
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ - ToCHWImage:
+ PostProcess:
+ name: Topk
+ topk: 5
+ class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+ Train:
+ - TopkAcc:
+ topk: [1, 5]
+ Eval:
+ - TopkAcc:
+ topk: [1, 5]
diff --git a/ppcls/configs/quick_start/ResNet50_vd_finetune.yaml b/ppcls/configs/quick_start/ResNet50_vd_finetune.yaml
deleted file mode 100644
index 76ea8decf..000000000
--- a/ppcls/configs/quick_start/ResNet50_vd_finetune.yaml
+++ /dev/null
@@ -1,69 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
-pretrained_model: "./pretrained/ResNet50_vd_pretrained"
-model_save_dir: "./output/"
-use_gpu: True
-classes_num: 102
-total_images: 1020
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 20
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.00375
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000001
-
-TRAIN:
- batch_size: 32
- num_workers: 0
- file_list: "./dataset/flowers102/train_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 20
- num_workers: 0
- file_list: "./dataset/flowers102/val_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/quick_start/ResNet50_vd_multilabel.yaml b/ppcls/configs/quick_start/ResNet50_vd_multilabel.yaml
deleted file mode 100644
index 32fed0b6a..000000000
--- a/ppcls/configs/quick_start/ResNet50_vd_multilabel.yaml
+++ /dev/null
@@ -1,77 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
-
-pretrained_model: "./pretrained/ResNet50_vd_pretrained"
-model_save_dir: "./output/"
-classes_num: 33
-total_images: 17463
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 10
-topk: 1
-image_shape: [3, 224, 224]
-
-multilabel: True
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.07
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000070
-
-TRAIN:
- batch_size: 256
- num_workers: 4
- file_list: "./dataset/NUS-WIDE-SCENE/NUS-SCENE-dataset/multilabel_train_list.txt"
- data_dir: "./dataset/NUS-WIDE-SCENE/NUS-SCENE-dataset/images"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
-
-VALID:
- batch_size: 64
- num_workers: 4
- file_list: "./dataset/NUS-WIDE-SCENE/NUS-SCENE-dataset/multilabel_test_list.txt"
- data_dir: "./dataset/NUS-WIDE-SCENE/NUS-SCENE-dataset/images"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
\ No newline at end of file
diff --git a/ppcls/configs/quick_start/ResNet50_vd_ssld_finetune.yaml b/ppcls/configs/quick_start/ResNet50_vd_ssld_finetune.yaml
deleted file mode 100644
index fda655faa..000000000
--- a/ppcls/configs/quick_start/ResNet50_vd_ssld_finetune.yaml
+++ /dev/null
@@ -1,71 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
- params:
- lr_mult_list: [0.5, 0.5, 0.6, 0.6, 0.8]
-pretrained_model: "./pretrained/ResNet50_vd_ssld_pretrained"
-model_save_dir: "./output/"
-use_gpu: True
-classes_num: 102
-total_images: 1020
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 20
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.00375
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000001
-
-TRAIN:
- batch_size: 32
- num_workers: 0
- file_list: "./dataset/flowers102/train_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
-VALID:
- batch_size: 20
- num_workers: 0
- file_list: "./dataset/flowers102/val_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/quick_start/ResNet50_vd_ssld_random_erasing_finetune.yaml b/ppcls/configs/quick_start/ResNet50_vd_ssld_random_erasing_finetune.yaml
deleted file mode 100644
index 7a60a45e5..000000000
--- a/ppcls/configs/quick_start/ResNet50_vd_ssld_random_erasing_finetune.yaml
+++ /dev/null
@@ -1,73 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
- params:
- lr_mult_list: [0.5, 0.5, 0.6, 0.6, 0.8]
-pretrained_model: "./pretrained/ResNet50_vd_ssld_pretrained"
-model_save_dir: "./output/"
-use_gpu: True
-classes_num: 102
-total_images: 1020
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 20
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.00375
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.000001
-
-TRAIN:
- batch_size: 32
- num_workers: 0
- file_list: "./dataset/flowers102/train_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 224
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- - RandomErasing:
- EPSILON: 0.5
-
-VALID:
- batch_size: 20
- num_workers: 0
- file_list: "./dataset/flowers102/val_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 256
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/quick_start/HRNet_W18_C_finetune_kunlun.yaml b/ppcls/configs/quick_start/kunlun/HRNet_W18_C_finetune_kunlun.yaml
similarity index 100%
rename from ppcls/configs/quick_start/HRNet_W18_C_finetune_kunlun.yaml
rename to ppcls/configs/quick_start/kunlun/HRNet_W18_C_finetune_kunlun.yaml
diff --git a/ppcls/configs/quick_start/ResNet50_vd_finetune_kunlun.yaml b/ppcls/configs/quick_start/kunlun/ResNet50_vd_finetune_kunlun.yaml
similarity index 100%
rename from ppcls/configs/quick_start/ResNet50_vd_finetune_kunlun.yaml
rename to ppcls/configs/quick_start/kunlun/ResNet50_vd_finetune_kunlun.yaml
diff --git a/ppcls/configs/quick_start/VGG16_finetune_kunlun.yaml b/ppcls/configs/quick_start/kunlun/VGG16_finetune_kunlun.yaml
similarity index 100%
rename from ppcls/configs/quick_start/VGG16_finetune_kunlun.yaml
rename to ppcls/configs/quick_start/kunlun/VGG16_finetune_kunlun.yaml
diff --git a/ppcls/configs/quick_start/VGG19_finetune_kunlun.yaml b/ppcls/configs/quick_start/kunlun/VGG19_finetune_kunlun.yaml
similarity index 100%
rename from ppcls/configs/quick_start/VGG19_finetune_kunlun.yaml
rename to ppcls/configs/quick_start/kunlun/VGG19_finetune_kunlun.yaml
diff --git a/ppcls/configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml b/ppcls/configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml
index c4f929cc0..ee5addcd4 100644
--- a/ppcls/configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml
+++ b/ppcls/configs/quick_start/new_user/ShuffleNetV2_x0_25.yaml
@@ -1,40 +1,54 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ShuffleNetV2_x0_25'
+# global configs
+Global:
+ checkpoints: null
+ pretrained_model: null
+ output_dir: ./output/
+ device: gpu
+ class_num: 102
+ save_interval: 1
+ eval_during_train: True
+ eval_interval: 1
+ epochs: 20
+ print_batch_step: 10
+ use_visualdl: False
+ # used for static mode and model export
+ image_shape: [3, 224, 224]
+ save_inference_dir: ./inference
-checkpoints: ""
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 102
-total_images: 1020
-save_interval: 1
-validate: True
-use_gpu: False
-valid_interval: 1
-epochs: 20
-topk: 5
-image_shape: [3, 224, 224]
+# model architecture
+Arch:
+ name: ShuffleNetV2_x0_25
+
+# loss function config for traing/eval process
+Loss:
+ Train:
+ - CELoss:
+ weight: 1.0
+ Eval:
+ - CELoss:
+ weight: 1.0
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.0125
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.00001
+Optimizer:
+ name: Momentum
+ momentum: 0.9
+ lr:
+ name: Cosine
+ learning_rate: 0.0125
+ warmup_epoch: 5
+ regularizer:
+ name: 'L2'
+ coeff: 0.00001
-TRAIN:
- batch_size: 32
- num_workers: 0
- file_list: "./dataset/flowers102/train_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
+
+# data loader for train and eval
+DataLoader:
+ Train:
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/flowers102/
+ cls_label_path: ./dataset/flowers102/train_list.txt
+ transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
@@ -43,19 +57,27 @@ TRAIN:
- RandFlipImage:
flip_code: 1
- NormalizeImage:
- scale: 1./255.
+ scale: 1.0/255.0
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- - ToCHWImage:
-VALID:
- batch_size: 20
- num_workers: 0
- file_list: "./dataset/flowers102/val_list.txt"
- data_dir: "./dataset/flowers102/"
- shuffle_seed: 0
- transforms:
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 256
+ drop_last: False
+ shuffle: True
+ loader:
+ num_workers: 4
+ use_shared_memory: True
+
+ Eval:
+ # TOTO: modify to the latest trainer
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/flowers102/
+ cls_label_path: ./dataset/flowers102/val_list.txt
+ transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
@@ -68,4 +90,40 @@ VALID:
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- - ToCHWImage:
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: False
+ loader:
+ num_workers: 4
+ use_shared_memory: True
+
+Infer:
+ infer_imgs: docs/images/whl/demo.jpg
+ batch_size: 10
+ transforms:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 256
+ - CropImage:
+ size: 224
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ - ToCHWImage:
+ PostProcess:
+ name: Topk
+ topk: 5
+
+Metric:
+ Train:
+ - TopkAcc:
+ topk: [1, 5]
+ Eval:
+ - TopkAcc:
+ topk: [1, 5]
diff --git a/ppcls/configs/quick_start/professional/MobileNetV3_large_x1_0_CIFAR100_finetune.yaml b/ppcls/configs/quick_start/professional/MobileNetV3_large_x1_0_CIFAR100_finetune.yaml
index 6cc50c98f..1b70d061b 100644
--- a/ppcls/configs/quick_start/professional/MobileNetV3_large_x1_0_CIFAR100_finetune.yaml
+++ b/ppcls/configs/quick_start/professional/MobileNetV3_large_x1_0_CIFAR100_finetune.yaml
@@ -2,29 +2,28 @@
Global:
checkpoints: null
pretrained_model: null
- output_dir: "./output/"
- device: "gpu"
+ output_dir: ./output/
+ device: gpu
class_num: 100
save_interval: 1
eval_during_train: True
eval_interval: 1
- epochs: 50
+ epochs: 100
print_batch_step: 10
use_visualdl: False
# used for static mode and model export
image_shape: [3, 32, 32]
- save_inference_dir: "./inference"
+ save_inference_dir: ./inference
# model architecture
Arch:
- name: "MobileNetV3_large_x1_0"
+ name: MobileNetV3_large_x1_0
# loss function config for traing/eval process
Loss:
Train:
- CELoss:
weight: 1.0
- epsilon: 0.1
Eval:
- CELoss:
weight: 1.0
@@ -45,83 +44,85 @@ Optimizer:
DataLoader:
Train:
dataset:
- name: ImageNetDataset
- image_root: "./dataset/CIFAR100/"
- cls_label_path: "./dataset/CIFAR100/train_list.txt"
- transform_ops:
- - RandCropImage:
- size: 32
- scale: [0.5, 1]
- ratio: [1, 1]
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 0.00392157
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
+ name: ImageNetDataset
+ image_root: ./dataset/CIFAR100/
+ cls_label_path: ./dataset/CIFAR100/train_list.txt
+ transform_ops:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - RandCropImage:
+ size: 32
+ - RandFlipImage:
+ flip_code: 1
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
sampler:
- name: DistributedBatchSampler
- batch_size: 1000
- drop_last: False
- shuffle: True
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: True
loader:
- num_workers: 6
- use_shared_memory: False
+ num_workers: 4
+ use_shared_memory: True
Eval:
# TOTO: modify to the latest trainer
dataset:
- name: ImageNetDataset
- image_root: "./dataset/CIFAR100/"
- cls_label_path: "./dataset/CIFAR100/test_list.txt"
- transform_ops:
- - ResizeImage:
- resize_short: 36
- - CropImage:
- size: 32
- - NormalizeImage:
- scale: 0.00392157
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
+ name: ImageNetDataset
+ image_root: ./dataset/CIFAR100/
+ cls_label_path: ./dataset/CIFAR100/test_list.txt
+ transform_ops:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 36
+ - CropImage:
+ size: 32
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
sampler:
- name: DistributedBatchSampler
- batch_size: 1000
- drop_last: False
- shuffle: False
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: False
loader:
- num_workers: 6
- use_shared_memory: False
+ num_workers: 4
+ use_shared_memory: True
Infer:
- infer_imgs: "docs/images/whl/demo.jpg"
+ infer_imgs: docs/images/whl/demo.jpg
batch_size: 10
transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 36
- - CropImage:
- size: 32
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 36
+ - CropImage:
+ size: 32
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ - ToCHWImage:
PostProcess:
name: Topk
topk: 5
- class_id_map_file: "ppcls/utils/imagenet1k_label_list.txt"
Metric:
- Train:
- - Topk:
- k: [1, 5]
- Eval:
- - Topk:
- k: [1, 5]
-
+ Train:
+ - TopkAcc:
+ topk: [1, 5]
+ Eval:
+ - TopkAcc:
+ topk: [1, 5]
diff --git a/ppcls/configs/quick_start/professional/R50_vd_distill_MV3_large_x1_0_CIFAR100.yaml b/ppcls/configs/quick_start/professional/R50_vd_distill_MV3_large_x1_0_CIFAR100.yaml
index f79714421..25166a260 100644
--- a/ppcls/configs/quick_start/professional/R50_vd_distill_MV3_large_x1_0_CIFAR100.yaml
+++ b/ppcls/configs/quick_start/professional/R50_vd_distill_MV3_large_x1_0_CIFAR100.yaml
@@ -1,73 +1,151 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd_distill_MobileNetV3_large_x1_0'
+# global configs
+Global:
+ checkpoints: null
+ pretrained_model: null
+ output_dir: "./output/"
+ device: "gpu"
+ class_num: 100
+ save_interval: 1
+ eval_during_train: True
+ eval_interval: 1
+ epochs: 100
+ print_batch_step: 10
+ use_visualdl: False
+ # used for static mode and model export
+ image_shape: [3, 32, 32]
+ save_inference_dir: "./inference"
-pretrained_model:
- - "./pretrained/CIFAR100_R50_vd_final/ppcls"
- - "./pretrained/MobileNetV3_large_x1_0_pretrained"
-model_save_dir: "./output/"
-classes_num: 100
-total_images: 50000
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 100
-topk: 5
-image_shape: [3, 32, 32]
+# model architecture
+Arch:
+ name: "DistillationModel"
+ # if not null, its lengths should be same as models
+ pretrained_list:
+ # if not null, its lengths should be same as models
+ freeze_params_list:
+ - True
+ - False
+ models:
+ - Teacher:
+ name: ResNet50_vd
+ pretrained: "./pretrained/best_model"
+ - Student:
+ name: MobileNetV3_large_x1_0
+ pretrained: True
-use_distillation: True
+ infer_model_name: "Student"
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.04
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
+# loss function config for traing/eval process
+Loss:
+ Train:
+ - DistillationCELoss:
+ weight: 1.0
+ model_name_pairs:
+ - ["Student", "Teacher"]
+ Eval:
+ - DistillationGTCELoss:
+ weight: 1.0
+ model_names: ["Student"]
+
-TRAIN:
- batch_size: 1024
- num_workers: 0
- file_list: "./dataset/CIFAR100/train_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 32
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
+Optimizer:
+ name: Momentum
+ momentum: 0.9
+ lr:
+ name: Cosine
+ learning_rate: 0.04
+ warmup_epoch: 5
+ regularizer:
+ name: 'L2'
+ coeff: 0.0001
-VALID:
- batch_size: 256
- num_workers: 0
- file_list: "./dataset/CIFAR100/test_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 36
- - CropImage:
- size: 32
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
+
+# data loader for train and eval
+DataLoader:
+ Train:
+ dataset:
+ name: ImageNetDataset
+ image_root: "./dataset/CIFAR100/"
+ cls_label_path: "./dataset/CIFAR100/train_list.txt"
+ transform_ops:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - RandCropImage:
+ size: 32
+ - RandFlipImage:
+ flip_code: 1
+ - NormalizeImage:
+ scale: 0.00392157
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 512
+ drop_last: False
+ shuffle: True
+ loader:
+ num_workers: 6
+ use_shared_memory: True
+
+ Eval:
+ # TOTO: modify to the latest trainer
+ dataset:
+ name: ImageNetDataset
+ image_root: "./dataset/CIFAR100/"
+ cls_label_path: "./dataset/CIFAR100/test_list.txt"
+ transform_ops:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 36
+ - CropImage:
+ size: 32
+ - NormalizeImage:
+ scale: 0.00392157
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: False
+ loader:
+ num_workers: 6
+ use_shared_memory: True
+
+Infer:
+ infer_imgs: "docs/images/whl/demo.jpg"
+ batch_size: 10
+ transforms:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 36
+ - CropImage:
+ size: 32
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ - ToCHWImage:
+ PostProcess:
+ name: DistillationPostProcess
+ func: Topk
+ topk: 5
+
+Metric:
+ Train:
+ - DistillationTopkAcc:
+ model_key: "Student"
+ topk: [1, 5]
+ Eval:
+ - DistillationTopkAcc:
+ model_key: "Student"
+ topk: [1, 5]
diff --git a/ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml b/ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml
index 9871f18f8..808856434 100644
--- a/ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml
+++ b/ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100.yaml
@@ -1,40 +1,53 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
+# global configs
+Global:
+ checkpoints: null
+ pretrained_model: null
+ output_dir: ./output/
+ device: gpu
+ class_num: 100
+ save_interval: 1
+ eval_during_train: True
+ eval_interval: 1
+ epochs: 100
+ print_batch_step: 10
+ use_visualdl: False
+ # used for static mode and model export
+ image_shape: [3, 32, 32]
+ save_inference_dir: ./inference
-checkpoints: ""
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 100
-total_images: 50000
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 100
-topk: 5
-image_shape: [3, 32, 32]
-use_mix: False
+# model architecture
+Arch:
+ name: ResNet50_vd
+
+# loss function config for traing/eval process
+Loss:
+ Train:
+ - CELoss:
+ weight: 1.0
+ Eval:
+ - CELoss:
+ weight: 1.0
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.04
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
+Optimizer:
+ name: Momentum
+ momentum: 0.9
+ lr:
+ name: Cosine
+ learning_rate: 0.04
+ regularizer:
+ name: 'L2'
+ coeff: 0.0001
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/CIFAR100/train_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
+
+# data loader for train and eval
+DataLoader:
+ Train:
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/CIFAR100/
+ cls_label_path: ./dataset/CIFAR100/train_list.txt
+ transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
@@ -43,24 +56,27 @@ TRAIN:
- RandFlipImage:
flip_code: 1
- NormalizeImage:
- scale: 1./255.
+ scale: 1.0/255.0
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- - ToCHWImage:
- mix:
- - MixupOperator:
- alpha: 0.2
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: True
+ loader:
+ num_workers: 4
+ use_shared_memory: True
-
-VALID:
- batch_size: 256
- num_workers: 0
- file_list: "./dataset/CIFAR100/test_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
+ Eval:
+ # TOTO: modify to the latest trainer
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/CIFAR100/
+ cls_label_path: ./dataset/CIFAR100/test_list.txt
+ transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
@@ -73,4 +89,40 @@ VALID:
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- - ToCHWImage:
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: False
+ loader:
+ num_workers: 4
+ use_shared_memory: True
+
+Infer:
+ infer_imgs: docs/images/whl/demo.jpg
+ batch_size: 10
+ transforms:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 36
+ - CropImage:
+ size: 32
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ - ToCHWImage:
+ PostProcess:
+ name: Topk
+ topk: 5
+
+Metric:
+ Train:
+ - TopkAcc:
+ topk: [1, 5]
+ Eval:
+ - TopkAcc:
+ topk: [1, 5]
diff --git a/ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100_finetune.yaml b/ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100_finetune.yaml
deleted file mode 100644
index 64c487e46..000000000
--- a/ppcls/configs/quick_start/professional/ResNet50_vd_CIFAR100_finetune.yaml
+++ /dev/null
@@ -1,76 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
-
-checkpoints: ""
-pretrained_model: "./pretrained/ResNet50_vd_pretrained"
-model_save_dir: "./output/"
-classes_num: 100
-total_images: 50000
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 100
-topk: 5
-image_shape: [3, 32, 32]
-use_mix: False
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.04
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/CIFAR100/train_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 32
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
- mix:
- - MixupOperator:
- alpha: 0.2
-
-
-VALID:
- batch_size: 256
- num_workers: 0
- file_list: "./dataset/CIFAR100/test_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 36
- - CropImage:
- size: 32
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
diff --git a/ppcls/configs/quick_start/professional/ResNet50_vd_mixup_CIFAR100_finetune.yaml b/ppcls/configs/quick_start/professional/ResNet50_vd_mixup_CIFAR100_finetune.yaml
index 1e77601d2..d7e9d25d6 100644
--- a/ppcls/configs/quick_start/professional/ResNet50_vd_mixup_CIFAR100_finetune.yaml
+++ b/ppcls/configs/quick_start/professional/ResNet50_vd_mixup_CIFAR100_finetune.yaml
@@ -1,40 +1,53 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
+# global configs
+Global:
+ checkpoints: null
+ pretrained_model: null
+ output_dir: ./output/
+ device: gpu
+ class_num: 100
+ save_interval: 1
+ eval_during_train: True
+ eval_interval: 1
+ epochs: 100
+ print_batch_step: 10
+ use_visualdl: False
+ # used for static mode and model export
+ image_shape: [3, 32, 32]
+ save_inference_dir: ./inference
-checkpoints: ""
-pretrained_model: "./pretrained/ResNet50_vd_pretrained"
-model_save_dir: "./output/"
-classes_num: 100
-total_images: 50000
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 100
-topk: 5
-image_shape: [3, 32, 32]
-use_mix: True
+# model architecture
+Arch:
+ name: ResNet50_vd
+
+# loss function config for traing/eval process
+Loss:
+ Train:
+ - CELoss:
+ weight: 1.0
+ Eval:
+ - CELoss:
+ weight: 1.0
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.04
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
+Optimizer:
+ name: Momentum
+ momentum: 0.9
+ lr:
+ name: Cosine
+ learning_rate: 0.04
+ regularizer:
+ name: 'L2'
+ coeff: 0.0001
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/CIFAR100/train_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
+
+# data loader for train and eval
+DataLoader:
+ Train:
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/CIFAR100/
+ cls_label_path: ./dataset/CIFAR100/train_list.txt
+ transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
@@ -43,24 +56,30 @@ TRAIN:
- RandFlipImage:
flip_code: 1
- NormalizeImage:
- scale: 1./255.
+ scale: 1.0/255.0
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- - ToCHWImage:
-
- mix:
+ batch_transform_ops:
- MixupOperator:
alpha: 0.2
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: True
+ loader:
+ num_workers: 4
+ use_shared_memory: True
-VALID:
- batch_size: 256
- num_workers: 0
- file_list: "./dataset/CIFAR100/test_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
+ Eval:
+ # TOTO: modify to the latest trainer
+ dataset:
+ name: ImageNetDataset
+ image_root: ./dataset/CIFAR100/
+ cls_label_path: ./dataset/CIFAR100/test_list.txt
+ transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
@@ -73,4 +92,37 @@ VALID:
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- - ToCHWImage:
+ sampler:
+ name: DistributedBatchSampler
+ batch_size: 64
+ drop_last: False
+ shuffle: False
+ loader:
+ num_workers: 4
+ use_shared_memory: True
+
+Infer:
+ infer_imgs: docs/images/whl/demo.jpg
+ batch_size: 10
+ transforms:
+ - DecodeImage:
+ to_rgb: True
+ channel_first: False
+ - ResizeImage:
+ resize_short: 36
+ - CropImage:
+ size: 32
+ - NormalizeImage:
+ scale: 1.0/255.0
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: ''
+ - ToCHWImage:
+ PostProcess:
+ name: Topk
+ topk: 5
+
+Metric:
+ Eval:
+ - TopkAcc:
+ topk: [1, 5]
diff --git a/ppcls/configs/quick_start/professional/ResNet50_vd_ssld_CIFAR100_finetune.yaml b/ppcls/configs/quick_start/professional/ResNet50_vd_ssld_CIFAR100_finetune.yaml
deleted file mode 100644
index 9e217185b..000000000
--- a/ppcls/configs/quick_start/professional/ResNet50_vd_ssld_CIFAR100_finetune.yaml
+++ /dev/null
@@ -1,76 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
- name: 'ResNet50_vd'
-
-checkpoints: ""
-pretrained_model: "./pretrained/ResNet50_vd_ssld_pretrained"
-model_save_dir: "./output/"
-classes_num: 100
-total_images: 50000
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 100
-topk: 5
-image_shape: [3, 32, 32]
-use_mix: False
-
-LEARNING_RATE:
- function: 'Cosine'
- params:
- lr: 0.04
-
-OPTIMIZER:
- function: 'Momentum'
- params:
- momentum: 0.9
- regularizer:
- function: 'L2'
- factor: 0.0001
-
-TRAIN:
- batch_size: 1024
- num_workers: 4
- file_list: "./dataset/CIFAR100/train_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - RandCropImage:
- size: 32
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1./255.
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
-
- mix:
- - MixupOperator:
- alpha: 0.2
-
-
-VALID:
- batch_size: 256
- num_workers: 0
- file_list: "./dataset/CIFAR100/test_list.txt"
- data_dir: "./dataset/CIFAR100/"
- shuffle_seed: 0
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- resize_short: 36
- - CropImage:
- size: 32
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage: