Wei Shengyu
GitHub
commit
961fdd2c52
|
|
@ -0,0 +1,36 @@
|
|||
Global:
|
||||
infer_imgs: "./images/PULC/car_exists/objects365_00001507.jpeg"
|
||||
inference_model_dir: "./models/car_exists_infer"
|
||||
batch_size: 1
|
||||
use_gpu: True
|
||||
enable_mkldnn: False
|
||||
cpu_num_threads: 10
|
||||
enable_benchmark: True
|
||||
use_fp16: False
|
||||
ir_optim: True
|
||||
use_tensorrt: False
|
||||
gpu_mem: 8000
|
||||
enable_profile: False
|
||||
|
||||
PreProcess:
|
||||
transform_ops:
|
||||
- ResizeImage:
|
||||
resize_short: 256
|
||||
- CropImage:
|
||||
size: 224
|
||||
- NormalizeImage:
|
||||
scale: 0.00392157
|
||||
mean: [0.485, 0.456, 0.406]
|
||||
std: [0.229, 0.224, 0.225]
|
||||
order: ''
|
||||
channel_num: 3
|
||||
- ToCHWImage:
|
||||
|
||||
PostProcess:
|
||||
main_indicator: ThreshOutput
|
||||
ThreshOutput:
|
||||
threshold: 0.5
|
||||
label_0: nocar
|
||||
label_1: contains_car
|
||||
SavePreLabel:
|
||||
save_dir: ./pre_label/
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 157 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 178 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 157 KiB |
|
|
@ -0,0 +1,447 @@
|
|||
# PULC 有人/无人分类模型
|
||||
|
||||
------
|
||||
|
||||
|
||||
## 目录
|
||||
|
||||
- [1. 模型和应用场景介绍](#1)
|
||||
- [2. 模型快速体验](#2)
|
||||
- [2.1 安装 paddleclas](#2.1)
|
||||
- [2.2 预测](#2.2)
|
||||
- [3. 模型训练、评估和预测](#3)
|
||||
- [3.1 环境配置](#3.1)
|
||||
- [3.2 数据准备](#3.2)
|
||||
- [3.2.1 数据集来源](#3.2.1)
|
||||
- [3.2.2 数据集获取](#3.2.2)
|
||||
- [3.3 模型训练](#3.3)
|
||||
- [3.4 模型评估](#3.4)
|
||||
- [3.5 模型预测](#3.5)
|
||||
- [4. 模型压缩](#4)
|
||||
- [4.1 SKL-UGI 知识蒸馏](#4.1)
|
||||
- [4.1.1 教师模型训练](#4.1.1)
|
||||
- [4.1.2 蒸馏训练](#4.1.2)
|
||||
- [5. 超参搜索](#5)
|
||||
- [6. 模型推理部署](#6)
|
||||
- [6.1 推理模型准备](#6.1)
|
||||
- [6.1.1 基于训练得到的权重导出 inference 模型](#6.1.1)
|
||||
- [6.1.2 直接下载 inference 模型](#6.1.2)
|
||||
- [6.2 基于 Python 预测引擎推理](#6.2)
|
||||
- [6.2.1 预测单张图像](#6.2.1)
|
||||
- [6.2.2 基于文件夹的批量预测](#6.2.2)
|
||||
- [6.3 基于 C++ 预测引擎推理](#6.3)
|
||||
- [6.4 服务化部署](#6.4)
|
||||
- [6.5 端侧部署](#6.5)
|
||||
- [6.6 Paddle2ONNX 模型转换与预测](#6.6)
|
||||
|
||||
|
||||
<a name="1"></a>
|
||||
|
||||
## 1. 模型和应用场景介绍
|
||||
|
||||
该案例提供了用户使用 PaddleClas 的超轻量图像分类方案（PULC，Practical Ultra Lightweight Classification）快速构建轻量级、高精度、可落地的有人/无人的分类模型。该模型可以广泛应用于如监控场景、人员进出管控场景、海量数据过滤场景等。
|
||||
|
||||
下表列出了判断图片中是否有车的二分类模型的相关指标，前两行展现了使用 SwinTranformer_tiny 和 MobileNetV3_small_x0_35 作为 backbone 训练得到的模型的相关指标，第三行至第六行依次展现了替换 backbone 为 PPLCNet_x1_0、使用 SSLD 预训练模型、使用 SSLD 预训练模型 + EDA 策略、使用 SSLD 预训练模型 + EDA 策略 + SKL-UGI 知识蒸馏策略训练得到的模型的相关指标。
|
||||
|
||||
|
||||
| 模型 | Tpr（%）@Fpr0.01 | 延时（ms） | 存储（M） | 策略 |
|
||||
|-------|----------------|----------|---------------|---------------|
|
||||
| SwinTranformer_tiny | 97.71 | 95.30 | 107 | 使用 ImageNet 预训练模型 |
|
||||
| MobileNetV3_small_x0_35 | 81.23 | 2.85 | 1.6 | 使用 ImageNet 预训练模型 |
|
||||
| PPLCNet_x1_0 | 94.72 | 2.12 | 6.5 | 使用 ImageNet 预训练模型 |
|
||||
| PPLCNet_x1_0 | 95.48 | 2.12 | 6.5 | 使用 SSLD 预训练模型 |
|
||||
| PPLCNet_x1_0 | 95.48 | 2.12 | 6.5 | 使用 SSLD 预训练模型+EDA 策略|
|
||||
| <b>PPLCNet_x1_0<b> | <b>95.92<b> | <b>2.12<b> | <b>6.5<b> | 使用 SSLD 预训练模型+EDA 策略+SKL-UGI 知识蒸馏策略|
|
||||
|
||||
从表中可以看出，backbone 为 SwinTranformer_tiny 时精度较高，但是推理速度较慢。将 backboone 替换为轻量级模型 MobileNetV3_small_x0_35 后，速度可以大幅提升，但是会导致精度大幅下降。将 backbone 替换为速度更快的 PPLCNet_x1_0 时，精度较 MobileNetV3_small_x0_35 高 13 个百分点，与此同时速度依旧可以快 20% 以上。在此基础上，使用 SSLD 预训练模型后，在不改变推理速度的前提下，精度可以提升约 0.7 个百分点，进一步地，在使用 SKL-UGI 知识蒸馏后，精度可以继续提升 0.44 个百分点。此时，PPLCNet_x1_0 达到了接近 SwinTranformer_tiny 模型的精度，但是速度快 40 多倍。关于 PULC 的训练方法和推理部署方法将在下面详细介绍。
|
||||
|
||||
**备注：**
|
||||
|
||||
* `Tpr`指标的介绍可以参考 [3.2 小节](#3.2)的备注部分，延时是基于 Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz 测试得到，开启 MKLDNN 加速策略，线程数为10。
|
||||
* 关于 PPLCNet 的介绍可以参考 [PPLCNet 介绍](../models/PP-LCNet.md)，相关论文可以查阅[PPLCNet paper](https://arxiv.org/abs/2109.15099)。
|
||||
|
||||
|
||||
<a name="2"></a>
|
||||
|
||||
## 2. 模型快速体验
|
||||
|
||||
<a name="2.1"></a>
|
||||
|
||||
### 2.1 安装 paddleclas
|
||||
|
||||
使用如下命令快速安装 paddlepaddle, paddleclas
|
||||
|
||||
```
|
||||
pip3 install paddlepaddle paddleclas
|
||||
```
|
||||
<a name="2.2"></a>
|
||||
|
||||
### 2.2 预测
|
||||
|
||||
* 使用命令行快速预测
|
||||
|
||||
```bash
|
||||
paddleclas --model_name=car_exists --infer_imgs=deploy/images/PULC/car_exists/objects365_00001507.jpeg
|
||||
```
|
||||
|
||||
结果如下：
|
||||
```
|
||||
>>> result
|
||||
class_ids: [1], scores: [0.9871138], label_names: ['contains_vehicle'], filename: deploy/images/PULC/car_exists/objects365_00001507.jpeg
|
||||
Predict complete!
|
||||
```
|
||||
|
||||
**备注**： 更换其他预测的数据时，只需要改变 `--infer_imgs=xx` 中的字段即可，支持传入整个文件夹。
|
||||
|
||||
|
||||
* 在 Python 代码中预测
|
||||
```python
|
||||
import paddleclas
|
||||
model = paddleclas.PaddleClas(model_name="car_exists")
|
||||
result = model.predict(input_data="deploy/images/PULC/car_exists/objects365_00001507.jpeg")
|
||||
print(next(result))
|
||||
```
|
||||
|
||||
**备注**：`model.predict()` 为可迭代对象（`generator`），因此需要使用 `next()` 函数或 `for` 循环对其迭代调用。每次调用将以 `batch_size` 为单位进行一次预测，并返回预测结果, 默认 `batch_size` 为 1，如果需要更改 `batch_size`，实例化模型时，需要指定 `batch_size`，如 `model = paddleclas.PaddleClas(model_name="car_exists", batch_size=2)`, 使用默认的代码返回结果示例如下：
|
||||
|
||||
```
|
||||
>>> result
|
||||
[{'class_ids': [1], 'scores': [0.9871138], 'label_names': ['contains_vehicle'], 'filename': 'deploy/images/PULC/car_exists/objects365_00001507.jpeg'}]
|
||||
```
|
||||
|
||||
<a name="3"></a>
|
||||
|
||||
## 3. 模型训练、评估和预测
|
||||
|
||||
<a name="3.1"></a>
|
||||
|
||||
### 3.1 环境配置
|
||||
|
||||
* 安装：请先参考文档[环境准备](../installation/install_paddleclas.md) 配置 PaddleClas 运行环境。
|
||||
|
||||
<a name="3.2"></a>
|
||||
|
||||
### 3.2 数据准备
|
||||
|
||||
<a name="3.2.1"></a>
|
||||
|
||||
#### 3.2.1 数据集来源
|
||||
|
||||
本案例中所使用的所有数据集均为开源数据，`train`和`val` 集合均为[Objects365 数据](https://www.objects365.org/overview.html)的训练集的子集，`ImageNet_val` 为[ImageNet-1k 数据](https://www.image-net.org/)的验证集。
|
||||
|
||||
<a name="3.2.2"></a>
|
||||
|
||||
#### 3.2.2 数据集获取
|
||||
|
||||
在公开数据集的基础上经过后处理即可得到本案例需要的数据，具体处理方法如下：
|
||||
|
||||
- 训练集合，本案例处理了 Objects365 数据训练集的标注文件，如果某张图含有“car”的标签，且这个框的面积在整张图中的比例大于 10%，即认为该张图中含有车，如果某张图中没有任何与交通工具，例如car、bus等相关的的标签，则认为该张图中不含有车。经过处理后，得到 108629 条可用数据，其中有车的数据有 27422 条，无车的数据 81207 条。
|
||||
|
||||
- 验证集合，处理方法与训练集相同，数据来源与 Objects365 数据集的验证集。为了测试结果准确，验证集经过人工校正，去除了一些可能存在标注错误的图像。
|
||||
|
||||
* 注：由于objects365的标签并不是完全互斥的，例如F1赛车可能是 "F1 Formula"，也可能被标称"car"。为了减轻干扰，我们仅保留"car"标签作为有车，而将不含任何交通工具的图作为无车。
|
||||
|
||||
处理后的数据集部分数据可视化如下：
|
||||
|
||||
|
||||
|
||||
此处提供了经过上述方法处理好的数据，可以直接下载得到。
|
||||
|
||||
|
||||
进入 PaddleClas 目录。
|
||||
|
||||
```
|
||||
cd path_to_PaddleClas
|
||||
```
|
||||
|
||||
进入 `dataset/` 目录，下载并解压有车/无车场景的数据。
|
||||
|
||||
```shell
|
||||
cd dataset
|
||||
wget https://paddleclas.bj.bcebos.com/data/PULC/car_exists.tar
|
||||
tar -xf car_exists.tar
|
||||
cd ../
|
||||
```
|
||||
|
||||
执行上述命令后，`dataset/` 下存在 `car_exists` 目录，该目录中具有以下数据：
|
||||
|
||||
```
|
||||
|
||||
├── objects365_car
|
||||
│ ├── objects365_00000039.jpg
|
||||
│ ├── objects365_00000099.jpg
|
||||
├── ImageNet_val
|
||||
│ ├── ILSVRC2012_val_00000001.JPEG
|
||||
│ ├── ILSVRC2012_val_00000002.JPEG
|
||||
...
|
||||
├── train_list.txt
|
||||
├── train_list.txt.debug
|
||||
├── train_list_for_distill.txt
|
||||
├── val_list.txt
|
||||
└── val_list.txt.debug
|
||||
```
|
||||
|
||||
其中 `train/` 和 `val/` 分别为训练集和验证集。`train_list.txt` 和 `val_list.txt` 分别为训练集和验证集的标签文件，`train_list.txt.debug` 和 `val_list.txt.debug` 分别为训练集和验证集的 `debug` 标签文件，其分别是 `train_list.txt` 和 `val_list.txt` 的子集，用该文件可以快速体验本案例的流程。`ImageNet_val/` 是 ImageNet-1k 的验证集，该集合和 `train` 集合的混合数据用于本案例的 `SKL-UGI知识蒸馏策略`，对应的训练标签文件为 `train_list_for_distill.txt` 。
|
||||
|
||||
**备注：**
|
||||
|
||||
* 关于 `train_list.txt`、`val_list.txt`的格式说明，可以参考 [PaddleClas 分类数据集格式说明](../data_preparation/classification_dataset.md#1-数据集格式说明) 。
|
||||
|
||||
* 关于如何得到蒸馏的标签文件可以参考[知识蒸馏标签获得方法](@ruoyu)。
|
||||
|
||||
|
||||
<a name="3.3"></a>
|
||||
|
||||
### 3.3 模型训练
|
||||
|
||||
|
||||
在 `ppcls/configs/PULC/car_exists/PPLCNet_x1_0.yaml` 中提供了基于该场景的训练配置，可以通过如下脚本启动训练：
|
||||
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES=0,1,2,3
|
||||
python3 -m paddle.distributed.launch \
|
||||
--gpus="0,1,2,3" \
|
||||
tools/train.py \
|
||||
-c ./ppcls/configs/PULC/car_exists/PPLCNet_x1_0.yaml
|
||||
```
|
||||
|
||||
验证集的最佳指标在 `0.95-0.96` 之间（数据集较小，容易造成波动）。
|
||||
|
||||
**备注：**
|
||||
|
||||
* 此时使用的指标为Tpr，该指标描述了在假正类率（Fpr）小于某一个指标时的真正类率（Tpr），是产业中二分类问题常用的指标之一。在本案例中，Fpr 为 1/100 。关于 Fpr 和 Tpr 的更多介绍，可以参考[这里](https://baike.baidu.com/item/AUC/19282953)。
|
||||
|
||||
* 在eval时，会打印出来当前最佳的 TprAtFpr 指标，具体地，其会打印当前的 `Fpr`、`Tpr` 值，以及当前的 `threshold`值，`Tpr` 值反映了在当前 `Fpr` 值下的召回率，该值越高，代表模型越好。`threshold` 表示当前最佳 `Fpr` 所对应的分类阈值，可用于后续模型部署落地等。
|
||||
|
||||
<a name="3.4"></a>
|
||||
|
||||
### 3.4 模型评估
|
||||
|
||||
训练好模型之后，可以通过以下命令实现对模型指标的评估。
|
||||
|
||||
```bash
|
||||
python3 tools/eval.py \
|
||||
-c ./ppcls/configs/PULC/car_exists/PPLCNet_x1_0.yaml \
|
||||
-o Global.pretrained_model="output/PPLCNet_x1_0/best_model"
|
||||
```
|
||||
|
||||
其中 `-o Global.pretrained_model="output/PPLCNet_x1_0/best_model"` 指定了当前最佳权重所在的路径，如果指定其他权重，只需替换对应的路径即可。
|
||||
|
||||
<a name="3.5"></a>
|
||||
|
||||
### 3.5 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.py \
|
||||
-c ./ppcls/configs/PULC/car_exists/PPLCNet_x1_0.yaml \
|
||||
-o Global.pretrained_model=output/PPLCNet_x1_0/best_model
|
||||
```
|
||||
|
||||
输出结果如下：
|
||||
|
||||
```
|
||||
[{'class_ids': [1], 'scores': [0.9871138], 'label_names': ['contains_vehicle'], 'filename': 'deploy/images/PULC/car_exists/objects365_00001507.jpeg'}]
|
||||
```
|
||||
|
||||
**备注：**
|
||||
|
||||
* 这里`-o Global.pretrained_model="output/PPLCNet_x1_0/best_model"` 指定了当前最佳权重所在的路径，如果指定其他权重，只需替换对应的路径即可。
|
||||
|
||||
* 默认是对 `deploy/images/PULC/car_exists/objects365_00001507.jpeg` 进行预测，此处也可以通过增加字段 `-o Infer.infer_imgs=xxx` 对其他图片预测。
|
||||
|
||||
* 二分类默认的阈值为0.5， 如果需要指定阈值，可以重写 `Infer.PostProcess.threshold` ，如`-o Infer.PostProcess.threshold=0.9794`，该值需要根据实际场景来确定，此处的 `0.9794` 是在该场景中的 `val` 数据集在千分之一 Fpr 下得到的最佳 Tpr 所得到的。
|
||||
|
||||
|
||||
<a name="4"></a>
|
||||
|
||||
## 4. 模型压缩
|
||||
|
||||
<a name="4.1"></a>
|
||||
|
||||
### 4.1 SKL-UGI 知识蒸馏
|
||||
|
||||
SKL-UGI 知识蒸馏是 PaddleClas 提出的一种简单有效的知识蒸馏方法，关于该方法的介绍，可以参考[SKL-UGI 知识蒸馏](@ruoyu)。
|
||||
|
||||
<a name="4.1.1"></a>
|
||||
|
||||
#### 4.1.1 教师模型训练
|
||||
|
||||
复用 `ppcls/configs/PULC/car_exists/PPLCNet/PPLCNet_x1_0.yaml` 中的超参数，训练教师模型，训练脚本如下：
|
||||
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES=0,1,2,3
|
||||
python3 -m paddle.distributed.launch \
|
||||
--gpus="0,1,2,3" \
|
||||
tools/train.py \
|
||||
-c ./ppcls/configs/PULC/car_exists/PPLCNet_x1_0.yaml \
|
||||
-o Arch.name=ResNet101_vd
|
||||
```
|
||||
|
||||
验证集的最佳指标为 `0.96-0.98` 之间，当前教师模型最好的权重保存在 `output/ResNet101_vd/best_model.pdparams`。
|
||||
|
||||
<a name="4.1.2"></a>
|
||||
|
||||
#### 4.1.2 蒸馏训练
|
||||
|
||||
配置文件`ppcls/configs/PULC/car_exists/PPLCNet_x1_0_distillation.yaml`提供了`SKL-UGI知识蒸馏策略`的配置。该配置将`ResNet101_vd`当作教师模型，`PPLCNet_x1_0`当作学生模型，使用ImageNet数据集的验证集作为新增的无标签数据。训练脚本如下：
|
||||
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES=0,1,2,3
|
||||
python3 -m paddle.distributed.launch \
|
||||
--gpus="0,1,2,3" \
|
||||
tools/train.py \
|
||||
-c ./ppcls/configs/PULC/car_exists/PPLCNet_x1_0_distillation.yaml \
|
||||
-o Arch.models.0.Teacher.pretrained=output/ResNet101_vd/best_model
|
||||
```
|
||||
|
||||
验证集的最佳指标为 `0.95-0.97` 之间，当前模型最好的权重保存在 `output/DistillationModel/best_model_student.pdparams`。
|
||||
|
||||
|
||||
<a name="5"></a>
|
||||
|
||||
## 5. 超参搜索
|
||||
|
||||
在 [3.2 节](#3.2)和 [4.1 节](#4.1)所使用的超参数是根据 PaddleClas 提供的 `SHAS 超参数搜索策略` 搜索得到的，如果希望在自己的数据集上得到更好的结果，可以参考[SHAS 超参数搜索策略](#TODO)来获得更好的训练超参数。
|
||||
|
||||
**备注：** 此部分内容是可选内容，搜索过程需要较长的时间，您可以根据自己的硬件情况来选择执行。如果没有更换数据集，可以忽略此节内容。
|
||||
|
||||
<a name="6"></a>
|
||||
|
||||
## 6. 模型推理部署
|
||||
|
||||
<a name="6.1"></a>
|
||||
|
||||
### 6.1 推理模型准备
|
||||
|
||||
Paddle Inference 是飞桨的原生推理库， 作用于服务器端和云端，提供高性能的推理能力。相比于直接基于预训练模型进行预测，Paddle Inference可使用 MKLDNN、CUDNN、TensorRT 进行预测加速，从而实现更优的推理性能。更多关于 Paddle Inference 推理引擎的介绍，可以参考 [Paddle Inference官网教程](https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/infer/inference/inference_cn.html)。
|
||||
|
||||
当使用 Paddle Inference 推理时，加载的模型类型为 inference 模型。本案例提供了两种获得 inference 模型的方法，如果希望得到和文档相同的结果，请选择[直接下载 inference 模型](#6.1.2)的方式。
|
||||
|
||||
<a name="6.1.1"></a>
|
||||
|
||||
### 6.1.1 基于训练得到的权重导出 inference 模型
|
||||
|
||||
此处，我们提供了将权重和模型转换的脚本，执行该脚本可以得到对应的 inference 模型：
|
||||
|
||||
```bash
|
||||
python3 tools/export_model.py \
|
||||
-c ./ppcls/configs/PULC/car_exists/PPLCNet_x1_0.yaml \
|
||||
-o Global.pretrained_model=output/DistillationModel/best_model_student \
|
||||
-o Global.save_inference_dir=deploy/models/PPLCNet_x1_0_car_exists_infer
|
||||
```
|
||||
执行完该脚本后会在 `deploy/models/` 下生成 `PPLCNet_x1_0_car_exists_infer` 文件夹，`models` 文件夹下应有如下文件结构：
|
||||
|
||||
```
|
||||
├── PPLCNet_x1_0_car_exists_infer
|
||||
│ ├── inference.pdiparams
|
||||
│ ├── inference.pdiparams.info
|
||||
│ └── inference.pdmodel
|
||||
```
|
||||
|
||||
**备注：** 此处的最佳权重是经过知识蒸馏后的权重路径，如果没有执行知识蒸馏的步骤，最佳模型保存在`output/PPLCNet_x1_0/best_model.pdparams`中。
|
||||
|
||||
<a name="6.1.2"></a>
|
||||
|
||||
### 6.1.2 直接下载 inference 模型
|
||||
|
||||
[6.1.1 小节](#6.1.1)提供了导出 inference 模型的方法，此处也提供了该场景可以下载的 inference 模型，可以直接下载体验。
|
||||
|
||||
```
|
||||
cd deploy/models
|
||||
# 下载 inference 模型并解压
|
||||
wget https://paddleclas.bj.bcebos.com/models/PULC/car_exists_infer.tar && tar -xf car_exists_infer.tar
|
||||
```
|
||||
|
||||
解压完毕后，`models` 文件夹下应有如下文件结构：
|
||||
|
||||
```
|
||||
├── car_exists_infer
|
||||
│ ├── inference.pdiparams
|
||||
│ ├── inference.pdiparams.info
|
||||
│ └── inference.pdmodel
|
||||
```
|
||||
|
||||
<a name="6.2"></a>
|
||||
|
||||
### 6.2 基于 Python 预测引擎推理
|
||||
|
||||
|
||||
<a name="6.2.1"></a>
|
||||
|
||||
#### 6.2.1 预测单张图像
|
||||
|
||||
返回 `deploy` 目录：
|
||||
|
||||
```
|
||||
cd ../
|
||||
```
|
||||
|
||||
运行下面的命令，对图像 `./images/PULC/car_exists/objects365_00001507.jpeg` 进行有人/无人分类。
|
||||
|
||||
```shell
|
||||
# 使用下面的命令使用 GPU 进行预测
|
||||
python3.7 python/predict_cls.py -c configs/PULC/car_exists/inference_car_exists.yaml
|
||||
# 使用下面的命令使用 CPU 进行预测
|
||||
python3.7 python/predict_cls.py -c configs/PULC/car_exists/inference_car_exists.yaml -o Global.use_gpu=False
|
||||
```
|
||||
|
||||
输出结果如下。
|
||||
|
||||
```
|
||||
objects365_00001507.jpeg: class id(s): [1], score(s): [0.99], label_name(s): ['contains_car']
|
||||
```
|
||||
|
||||
|
||||
**备注：** 二分类默认的阈值为0.5， 如果需要指定阈值，可以重写 `Infer.PostProcess.threshold` ，如`-o Infer.PostProcess.threshold=0.9794`，该值需要根据实际场景来确定，此处的 `0.9794` 是在该场景中的 `val` 数据集在千分之一 Fpr 下得到的最佳 Tpr 所得到的。该阈值的确定方法可以参考[3.3节](#3.3)备注部分。
|
||||
|
||||
<a name="6.2.2"></a>
|
||||
|
||||
#### 6.2.2 基于文件夹的批量预测
|
||||
|
||||
如果希望预测文件夹内的图像，可以直接修改配置文件中的 `Global.infer_imgs` 字段，也可以通过下面的 `-o` 参数修改对应的配置。
|
||||
|
||||
```shell
|
||||
# 使用下面的命令使用 GPU 进行预测，如果希望使用 CPU 预测，可以在命令后面添加 -o Global.use_gpu=False
|
||||
python3.7 python/predict_cls.py -c configs/PULC/car_exists/inference_car_exists.yaml -o Global.infer_imgs="./images/PULC/car_exists/"
|
||||
```
|
||||
|
||||
终端中会输出该文件夹内所有图像的分类结果，如下所示。
|
||||
|
||||
```
|
||||
objects365_00001507.jpeg: class id(s): [1], score(s): [0.99], label_name(s): ['contains_car']
|
||||
objects365_00001521.jpeg: class id(s): [0], score(s): [0.99], label_name(s): ['nocar']
|
||||
```
|
||||
|
||||
其中，`contains_car` 表示该图里存在车，`nocar` 表示该图里不存在车。
|
||||
|
||||
<a name="6.3"></a>
|
||||
|
||||
### 6.3 基于 C++ 预测引擎推理
|
||||
|
||||
PaddleClas 提供了基于 C++ 预测引擎推理的示例，您可以参考[服务器端 C++ 预测](../inference_deployment/cpp_deploy.md)来完成相应的推理部署。如果您使用的是 Windows 平台，可以参考[基于 Visual Studio 2019 Community CMake 编译指南](../inference_deployment/cpp_deploy_on_windows.md)完成相应的预测库编译和模型预测工作。
|
||||
|
||||
<a name="6.4"></a>
|
||||
|
||||
### 6.4 服务化部署
|
||||
|
||||
Paddle Serving 提供高性能、灵活易用的工业级在线推理服务。Paddle Serving 支持 RESTful、gRPC、bRPC 等多种协议，提供多种异构硬件和多种操作系统环境下推理解决方案。更多关于Paddle Serving 的介绍，可以参考[Paddle Serving 代码仓库](https://github.com/PaddlePaddle/Serving)。
|
||||
|
||||
PaddleClas 提供了基于 Paddle Serving 来完成模型服务化部署的示例，您可以参考[模型服务化部署](../inference_deployment/paddle_serving_deploy.md)来完成相应的部署工作。
|
||||
|
||||
<a name="6.5"></a>
|
||||
|
||||
### 6.5 端侧部署
|
||||
|
||||
Paddle Lite 是一个高性能、轻量级、灵活性强且易于扩展的深度学习推理框架，定位于支持包括移动端、嵌入式以及服务器端在内的多硬件平台。更多关于 Paddle Lite 的介绍，可以参考[Paddle Lite 代码仓库](https://github.com/PaddlePaddle/Paddle-Lite)。
|
||||
|
||||
PaddleClas 提供了基于 Paddle Lite 来完成模型端侧部署的示例，您可以参考[端侧部署](../inference_deployment/paddle_lite_deploy.md)来完成相应的部署工作。
|
||||
|
||||
<a name="6.6"></a>
|
||||
|
||||
### 6.6 Paddle2ONNX 模型转换与预测
|
||||
|
||||
Paddle2ONNX 支持将 PaddlePaddle 模型格式转化到 ONNX 模型格式。通过 ONNX 可以完成将 Paddle 模型到多种推理引擎的部署，包括TensorRT/OpenVINO/MNN/TNN/NCNN，以及其它对 ONNX 开源格式进行支持的推理引擎或硬件。更多关于 Paddle2ONNX 的介绍，可以参考[Paddle2ONNX 代码仓库](https://github.com/PaddlePaddle/Paddle2ONNX)。
|
||||
|
||||
PaddleClas 提供了基于 Paddle2ONNX 来完成 inference 模型转换 ONNX 模型并作推理预测的示例，您可以参考[Paddle2ONNX 模型转换与预测](@shuilong)来完成相应的部署工作。
|
||||
|
|
@ -0,0 +1,139 @@
|
|||
# global configs
|
||||
Global:
|
||||
checkpoints: null
|
||||
pretrained_model: null
|
||||
output_dir: ./output/
|
||||
device: gpu
|
||||
save_interval: 1
|
||||
eval_during_train: True
|
||||
eval_interval: 1
|
||||
start_eval_epoch: 10
|
||||
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
|
||||
# training model under @to_static
|
||||
to_static: False
|
||||
use_dali: False
|
||||
|
||||
# model architecture
|
||||
Arch:
|
||||
name: MobileNetV3_small_x0_35
|
||||
class_num: 2
|
||||
pretrained: True
|
||||
use_sync_bn: True
|
||||
|
||||
# loss function config for traing/eval process
|
||||
Loss:
|
||||
Train:
|
||||
- CELoss:
|
||||
weight: 1.0
|
||||
epsilon: 0.1
|
||||
Eval:
|
||||
- CELoss:
|
||||
weight: 1.0
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Momentum
|
||||
momentum: 0.9
|
||||
lr:
|
||||
name: Cosine
|
||||
learning_rate: 0.05
|
||||
warmup_epoch: 5
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
coeff: 0.00001
|
||||
|
||||
|
||||
# data loader for train and eval
|
||||
DataLoader:
|
||||
Train:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists/
|
||||
cls_label_path: ./dataset/car_exists/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: 512
|
||||
drop_last: False
|
||||
shuffle: True
|
||||
loader:
|
||||
num_workers: 8
|
||||
use_shared_memory: True
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists/
|
||||
cls_label_path: ./dataset/car_exists/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: deploy/images/PULC/car_exists/objects365_00001507.jpeg
|
||||
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: ThreshOutput
|
||||
threshold: 0.5
|
||||
label_0: nobody
|
||||
label_1: someone
|
||||
|
||||
Metric:
|
||||
Train:
|
||||
- TopkAcc:
|
||||
topk: [1, 2]
|
||||
Eval:
|
||||
- TprAtFpr:
|
||||
max_fpr: 0.01
|
||||
- TopkAcc:
|
||||
topk: [1, 2]
|
||||
|
|
@ -0,0 +1,152 @@
|
|||
# global configs
|
||||
Global:
|
||||
checkpoints: null
|
||||
pretrained_model: null
|
||||
output_dir: ./output/
|
||||
device: gpu
|
||||
save_interval: 1
|
||||
eval_during_train: True
|
||||
eval_interval: 1
|
||||
start_eval_epoch: 10
|
||||
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
|
||||
# training model under @to_static
|
||||
to_static: False
|
||||
use_dali: False
|
||||
|
||||
|
||||
# model architecture
|
||||
Arch:
|
||||
name: PPLCNet_x1_0
|
||||
class_num: 2
|
||||
pretrained: True
|
||||
use_ssld: True
|
||||
use_sync_bn: True
|
||||
|
||||
# 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: 0.0125
|
||||
warmup_epoch: 5
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
coeff: 0.00004
|
||||
|
||||
|
||||
# data loader for train and eval
|
||||
DataLoader:
|
||||
Train:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists/
|
||||
cls_label_path: ./dataset/car_exists/train_list.txt
|
||||
transform_ops:
|
||||
- DecodeImage:
|
||||
to_rgb: True
|
||||
channel_first: False
|
||||
- RandCropImage:
|
||||
size: 192
|
||||
- RandFlipImage:
|
||||
flip_code: 1
|
||||
- TimmAutoAugment:
|
||||
prob: 0.5
|
||||
config_str: rand-m9-mstd0.5-inc1
|
||||
interpolation: bicubic
|
||||
img_size: 192
|
||||
- NormalizeImage:
|
||||
scale: 1.0/255.0
|
||||
mean: [0.485, 0.456, 0.406]
|
||||
std: [0.229, 0.224, 0.225]
|
||||
order: ''
|
||||
- RandomErasing:
|
||||
EPSILON: 0.5
|
||||
sl: 0.02
|
||||
sh: 1.0/3.0
|
||||
r1: 0.3
|
||||
attempt: 10
|
||||
use_log_aspect: True
|
||||
mode: pixel
|
||||
sampler:
|
||||
name: DistributedBatchSampler
|
||||
batch_size: 64
|
||||
drop_last: False
|
||||
shuffle: True
|
||||
loader:
|
||||
num_workers: 8
|
||||
use_shared_memory: True
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists
|
||||
cls_label_path: ./dataset/car_exists/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: deploy/images/PULC/car_exists/objects365_00001507.jpeg
|
||||
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: ThreshOutput
|
||||
threshold: 0.9
|
||||
label_0: nobody
|
||||
label_1: someone
|
||||
|
||||
Metric:
|
||||
Train:
|
||||
- TopkAcc:
|
||||
topk: [1, 2]
|
||||
Eval:
|
||||
- TprAtFpr:
|
||||
max_fpr: 0.01
|
||||
- TopkAcc:
|
||||
topk: [1, 2]
|
||||
|
|
@ -0,0 +1,169 @@
|
|||
# global configs
|
||||
Global:
|
||||
checkpoints: null
|
||||
pretrained_model: null
|
||||
output_dir: ./output
|
||||
device: gpu
|
||||
save_interval: 1
|
||||
eval_during_train: True
|
||||
start_eval_epoch: 1
|
||||
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
|
||||
# training model under @to_static
|
||||
to_static: False
|
||||
use_dali: False
|
||||
|
||||
# model architecture
|
||||
Arch:
|
||||
name: "DistillationModel"
|
||||
class_num: &class_num 2
|
||||
# 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
|
||||
use_sync_bn: True
|
||||
models:
|
||||
- Teacher:
|
||||
name: ResNet101_vd
|
||||
class_num: *class_num
|
||||
- Student:
|
||||
name: PPLCNet_x1_0
|
||||
class_num: *class_num
|
||||
pretrained: True
|
||||
use_ssld: True
|
||||
|
||||
infer_model_name: "Student"
|
||||
|
||||
# loss function config for traing/eval process
|
||||
Loss:
|
||||
Train:
|
||||
- DistillationDMLLoss:
|
||||
weight: 1.0
|
||||
model_name_pairs:
|
||||
- ["Student", "Teacher"]
|
||||
Eval:
|
||||
- CELoss:
|
||||
weight: 1.0
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Momentum
|
||||
momentum: 0.9
|
||||
lr:
|
||||
name: Cosine
|
||||
learning_rate: 0.01
|
||||
warmup_epoch: 5
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
coeff: 0.00004
|
||||
|
||||
|
||||
# data loader for train and eval
|
||||
DataLoader:
|
||||
Train:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists/
|
||||
cls_label_path: ./dataset/car_exists/train_list_for_distill.txt
|
||||
transform_ops:
|
||||
- DecodeImage:
|
||||
to_rgb: True
|
||||
channel_first: False
|
||||
- RandCropImage:
|
||||
size: 192
|
||||
- RandFlipImage:
|
||||
flip_code: 1
|
||||
- TimmAutoAugment:
|
||||
prob: 0.0
|
||||
config_str: rand-m9-mstd0.5-inc1
|
||||
interpolation: bicubic
|
||||
img_size: 192
|
||||
- NormalizeImage:
|
||||
scale: 1.0/255.0
|
||||
mean: [0.485, 0.456, 0.406]
|
||||
std: [0.229, 0.224, 0.225]
|
||||
order: ''
|
||||
- RandomErasing:
|
||||
EPSILON: 0.1
|
||||
sl: 0.02
|
||||
sh: 1.0/3.0
|
||||
r1: 0.3
|
||||
attempt: 10
|
||||
use_log_aspect: True
|
||||
mode: pixel
|
||||
sampler:
|
||||
name: DistributedBatchSampler
|
||||
batch_size: 64
|
||||
drop_last: False
|
||||
shuffle: True
|
||||
loader:
|
||||
num_workers: 16
|
||||
use_shared_memory: True
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists/
|
||||
cls_label_path: ./dataset/car_exists/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: deploy/images/PULC/car_exists/objects365_00001507.jpeg
|
||||
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: ThreshOutput
|
||||
threshold: 0.5
|
||||
label_0: nobody
|
||||
label_1: someone
|
||||
|
||||
Metric:
|
||||
Train:
|
||||
- DistillationTopkAcc:
|
||||
model_key: "Student"
|
||||
topk: [1, 2]
|
||||
Eval:
|
||||
- TprAtFpr:
|
||||
max_fpr: 0.01
|
||||
- TopkAcc:
|
||||
topk: [1, 2]
|
||||
|
|
@ -0,0 +1,152 @@
|
|||
# global configs
|
||||
Global:
|
||||
checkpoints: null
|
||||
pretrained_model: null
|
||||
output_dir: ./output/
|
||||
device: gpu
|
||||
save_interval: 1
|
||||
eval_during_train: True
|
||||
eval_interval: 1
|
||||
start_eval_epoch: 10
|
||||
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
|
||||
# training model under @to_static
|
||||
to_static: False
|
||||
use_dali: False
|
||||
|
||||
|
||||
# model architecture
|
||||
Arch:
|
||||
name: PPLCNet_x1_0
|
||||
class_num: 2
|
||||
pretrained: True
|
||||
use_ssld: True
|
||||
use_sync_bn: True
|
||||
|
||||
# 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: 0.01
|
||||
warmup_epoch: 5
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
coeff: 0.00004
|
||||
|
||||
|
||||
# data loader for train and eval
|
||||
DataLoader:
|
||||
Train:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists/
|
||||
cls_label_path: ./dataset/car_exists/train_list.txt
|
||||
transform_ops:
|
||||
- DecodeImage:
|
||||
to_rgb: True
|
||||
channel_first: False
|
||||
- RandCropImage:
|
||||
size: 224
|
||||
- RandFlipImage:
|
||||
flip_code: 1
|
||||
- TimmAutoAugment:
|
||||
prob: 0.0
|
||||
config_str: rand-m9-mstd0.5-inc1
|
||||
interpolation: bicubic
|
||||
img_size: 224
|
||||
- NormalizeImage:
|
||||
scale: 1.0/255.0
|
||||
mean: [0.485, 0.456, 0.406]
|
||||
std: [0.229, 0.224, 0.225]
|
||||
order: ''
|
||||
- RandomErasing:
|
||||
EPSILON: 0.0
|
||||
sl: 0.02
|
||||
sh: 1.0/3.0
|
||||
r1: 0.3
|
||||
attempt: 10
|
||||
use_log_aspect: True
|
||||
mode: pixel
|
||||
sampler:
|
||||
name: DistributedBatchSampler
|
||||
batch_size: 64
|
||||
drop_last: False
|
||||
shuffle: True
|
||||
loader:
|
||||
num_workers: 8
|
||||
use_shared_memory: True
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists/
|
||||
cls_label_path: ./dataset/car_exists/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: deploy/images/PULC/car_exists/objects365_00001507.jpeg
|
||||
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: ThreshOutput
|
||||
threshold: 0.5
|
||||
label_0: nobody
|
||||
label_1: someone
|
||||
|
||||
Metric:
|
||||
Train:
|
||||
- TopkAcc:
|
||||
topk: [1, 2]
|
||||
Eval:
|
||||
- TprAtFpr:
|
||||
max_fpr: 0.01
|
||||
- TopkAcc:
|
||||
topk: [1, 2]
|
||||
|
|
@ -0,0 +1,169 @@
|
|||
# global configs
|
||||
Global:
|
||||
checkpoints: null
|
||||
pretrained_model: null
|
||||
output_dir: ./output/
|
||||
device: gpu
|
||||
save_interval: 1
|
||||
eval_during_train: True
|
||||
eval_interval: 1
|
||||
start_eval_epoch: 10
|
||||
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
|
||||
# training model under @to_static
|
||||
to_static: False
|
||||
use_dali: False
|
||||
|
||||
# mixed precision training
|
||||
AMP:
|
||||
scale_loss: 128.0
|
||||
use_dynamic_loss_scaling: True
|
||||
# O1: mixed fp16
|
||||
level: O1
|
||||
|
||||
# model architecture
|
||||
Arch:
|
||||
name: SwinTransformer_tiny_patch4_window7_224
|
||||
class_num: 2
|
||||
pretrained: True
|
||||
|
||||
# loss function config for traing/eval process
|
||||
Loss:
|
||||
Train:
|
||||
- CELoss:
|
||||
weight: 1.0
|
||||
epsilon: 0.1
|
||||
Eval:
|
||||
- CELoss:
|
||||
weight: 1.0
|
||||
|
||||
Optimizer:
|
||||
name: AdamW
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
epsilon: 1e-8
|
||||
weight_decay: 0.05
|
||||
no_weight_decay_name: absolute_pos_embed relative_position_bias_table .bias norm
|
||||
one_dim_param_no_weight_decay: True
|
||||
lr:
|
||||
name: Cosine
|
||||
learning_rate: 1e-4
|
||||
eta_min: 2e-6
|
||||
warmup_epoch: 5
|
||||
warmup_start_lr: 2e-7
|
||||
|
||||
|
||||
# data loader for train and eval
|
||||
DataLoader:
|
||||
Train:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists/
|
||||
cls_label_path: ./dataset/car_exists/train_list.txt
|
||||
transform_ops:
|
||||
- DecodeImage:
|
||||
to_rgb: True
|
||||
channel_first: False
|
||||
- RandCropImage:
|
||||
size: 224
|
||||
interpolation: bicubic
|
||||
backend: pil
|
||||
- RandFlipImage:
|
||||
flip_code: 1
|
||||
- TimmAutoAugment:
|
||||
config_str: rand-m9-mstd0.5-inc1
|
||||
interpolation: bicubic
|
||||
img_size: 224
|
||||
- NormalizeImage:
|
||||
scale: 1.0/255.0
|
||||
mean: [0.485, 0.456, 0.406]
|
||||
std: [0.229, 0.224, 0.225]
|
||||
order: ''
|
||||
- RandomErasing:
|
||||
EPSILON: 0.25
|
||||
sl: 0.02
|
||||
sh: 1.0/3.0
|
||||
r1: 0.3
|
||||
attempt: 10
|
||||
use_log_aspect: True
|
||||
mode: pixel
|
||||
batch_transform_ops:
|
||||
- OpSampler:
|
||||
MixupOperator:
|
||||
alpha: 0.8
|
||||
prob: 0.5
|
||||
CutmixOperator:
|
||||
alpha: 1.0
|
||||
prob: 0.5
|
||||
sampler:
|
||||
name: DistributedBatchSampler
|
||||
batch_size: 128
|
||||
drop_last: False
|
||||
shuffle: True
|
||||
loader:
|
||||
num_workers: 8
|
||||
use_shared_memory: True
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: ImageNetDataset
|
||||
image_root: ./dataset/car_exists/
|
||||
cls_label_path: ./dataset/car_exists/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: 8
|
||||
use_shared_memory: True
|
||||
|
||||
Infer:
|
||||
infer_imgs: deploy/images/PULC/car_exists/objects365_00001507.jpeg
|
||||
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: ThreshOutput
|
||||
threshold: 0.5
|
||||
label_0: nobody
|
||||
label_1: someone
|
||||
|
||||
Metric:
|
||||
Train:
|
||||
- TopkAcc:
|
||||
topk: [1, 2]
|
||||
Eval:
|
||||
- TprAtFpr:
|
||||
max_fpr: 0.01
|
||||
- TopkAcc:
|
||||
topk: [1, 2]
|
||||
|
|
@ -0,0 +1,40 @@
|
|||
base_config_file: ppcls/configs/PULC/person_exists/PPLCNet_x1_0_search.yaml
|
||||
distill_config_file: ppcls/configs/PULC/person_exists/PPLCNet_x1_0_distillation.yaml
|
||||
|
||||
gpus: 0,1,2,3
|
||||
output_dir: output/search_person_cls
|
||||
search_times: 1
|
||||
search_dict:
|
||||
- search_key: lrs
|
||||
replace_config:
|
||||
- Optimizer.lr.learning_rate
|
||||
search_values: [0.0075, 0.01, 0.0125]
|
||||
- search_key: resolutions
|
||||
replace_config:
|
||||
- DataLoader.Train.dataset.transform_ops.1.RandCropImage.size
|
||||
- DataLoader.Train.dataset.transform_ops.3.TimmAutoAugment.img_size
|
||||
search_values: [176, 192, 224]
|
||||
- search_key: ra_probs
|
||||
replace_config:
|
||||
- DataLoader.Train.dataset.transform_ops.3.TimmAutoAugment.prob
|
||||
search_values: [0.0, 0.1, 0.5]
|
||||
- search_key: re_probs
|
||||
replace_config:
|
||||
- DataLoader.Train.dataset.transform_ops.5.RandomErasing.EPSILON
|
||||
search_values: [0.0, 0.1, 0.5]
|
||||
- search_key: lr_mult_list
|
||||
replace_config:
|
||||
- Arch.lr_mult_list
|
||||
search_values:
|
||||
- [0.0, 0.2, 0.4, 0.6, 0.8, 1.0]
|
||||
- [0.0, 0.4, 0.4, 0.8, 0.8, 1.0]
|
||||
- [1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
|
||||
teacher:
|
||||
rm_keys:
|
||||
- Arch.lr_mult_list
|
||||
search_values:
|
||||
- ResNet101_vd
|
||||
- ResNet50_vd
|
||||
final_replace:
|
||||
Arch.lr_mult_list: Arch.models.1.Student.lr_mult_list
|
||||
|
||||
Loading…
Reference in New Issue