mirrors
/
PaddleClas
mirror of https://github.com/PaddlePaddle/PaddleClas.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

rename v2 to V2

pull/2761/head
Yang Nie 2023-04-17 16:39:18 +08:00 committed by Tingquan Gao
parent be6a22be18
commit deb8e98779
13 changed files with 70 additions and 73 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/zh_CN/models/ImageNet1k/MobileViTv2.md → docs/zh_CN/models/ImageNet1k/MobileViTV2.md
View File

@ -1,4 +1,4 @@
# MobileViTv2
# MobileViTV2
-----
## 目录
@ -24,8 +24,7 @@
### 1.1 模型简介
MobileViTv2 是一个结合 CNN 和 ViT 的轻量级模型，用于移动视觉任务。通过 MobileViTv2-block 解决了 MobileViTv1 的扩展问题并简化了学习任务，从而得倒了 MobileViTv2-XXS、XS 和 S 模型，在 ImageNet-1k、ADE20K、COCO 和 PascalVOC2012 数据集上表现优于 MobileViTv1。
通过将提出的融合块添加到 MobileViTv2 中，创建 MobileViTv2-0.5、0.75 和 1.0 模型，在ImageNet-1k、ADE20K、COCO和PascalVOC2012数据集上给出了比 MobileViTv2 更好的准确性数据。[论文地址](https://arxiv.org/abs/2209.15159)。
MobileViT 中的主要效率瓶颈是Transformer中的多头自注意力，影响资源受限设备上的延迟。MobileViTV2 提出了一种具有线性复杂度的可分离自我注意力方法，它使用一个简单而有效的逐元素操作来计算自我注意力，使其成为资源受限设备的良好选择，在移动设备上运行时比MobileViT快3.2倍。[论文地址](https://arxiv.org/abs/2206.02680)。
<a name='1.2'></a>
@ -33,10 +32,10 @@ MobileViTv2 是一个结合 CNN 和 ViT 的轻量级模型，用于移动视觉
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPs<br>(G) | Params<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| MobileViTv2_x0_5 | 0.7017 | 0.89884 | 0.7018 | - | 480.46 | 1.37 |
| MobileViTv2_x1_0 | 0.7813 | 0.94172 | 0.7809 | - | 1843.81 | 4.90 |
| MobileViTv2_x1_5 | 0.8034 | 0.95094 | 0.8038 | - | 4090.07 | 10.60 |
| MobileViTv2_x2_0 | 0.8116 | 0.95370 | 0.8117 | - | 7219.23 | 18.45 |
| MobileViTV2_x0_5 | 0.7017 | 0.89884 | 0.7018 | - | 480.46 | 1.37 |
| MobileViTV2_x1_0 | 0.7813 | 0.94172 | 0.7809 | - | 1843.81 | 4.90 |
| MobileViTV2_x1_5 | 0.8034 | 0.95094 | 0.8038 | - | 4090.07 | 10.60 |
| MobileViTV2_x2_0 | 0.8116 | 0.95370 | 0.8117 | - | 7219.23 | 18.45 |
**备注：** PaddleClas 所提供的该系列模型的预训练模型权重，均是基于其官方提供的权重转得。
@ -50,7 +49,7 @@ MobileViTv2 是一个结合 CNN 和 ViT 的轻量级模型，用于移动视觉
## 3. 模型训练、评估和预测
此部分内容包括训练环境配置、ImageNet数据的准备、该模型在 ImageNet 上的训练、评估、预测等内容。在 `ppcls/configs/ImageNet/MobileViTv2/` 中提供了该模型的训练配置，启动训练方法可以参考：[ResNet50 模型训练、评估和预测](./ResNet.md#3-模型训练评估和预测)。
此部分内容包括训练环境配置、ImageNet数据的准备、该模型在 ImageNet 上的训练、评估、预测等内容。在 `ppcls/configs/ImageNet/MobileViTV2/` 中提供了该模型的训练配置，启动训练方法可以参考：[ResNet50 模型训练、评估和预测](./ResNet.md#3-模型训练评估和预测)。
**备注：** 由于 MobileViT 系列模型默认使用的 GPU 数量为 8 个，所以在训练时，需要指定8个GPU，如`python3 -m paddle.distributed.launch --gpus="0,1,2,3,4,5,6,7" tools/train.py -c xxx.yaml`, 如果使用 4 个 GPU 训练，默认学习率需要减小一半，精度可能有损。

18
docs/zh_CN/models/ImageNet1k/README.md
View File

@ -796,19 +796,19 @@ DeiT（Data-efficient Image Transformers）系列模型的精度、速度指标
<a name="MobileViT"></a>
## MobileViT 系列 <sup>[[42](#ref42)][[51](#ref51)]</sup>
## MobileViT 系列 <sup>[[42](#ref42)][[51](#ref51)][[52](#ref52)]</sup>
关于 MobileViT 系列模型的精度、速度指标如下表所示，更多介绍可以参考：[MobileViT 系列模型文档](MobileViT.md)，[MobileViTv2 系列模型文档](MobileViTv2.md)，[MobileViTv3 系列模型文档](MobileViTv3.md)。
关于 MobileViT 系列模型的精度、速度指标如下表所示，更多介绍可以参考：[MobileViT 系列模型文档](MobileViT.md)，[MobileViTV2 系列模型文档](MobileViTV2.md)，[MobileViTv3 系列模型文档](MobileViTv3.md)。
| 模型 | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(M) | Params(M) | 预训练模型下载地址 | inference模型下载地址 |
| ---------- | --------- | --------- | ---------------- | ---------------- | -------- | --------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| MobileViT_XXS | 0.6867 | 0.8878 | - | - | - | 337.24 | 1.28 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileViT_XXS_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/MobileViT_XXS_infer.tar) |
| MobileViT_XS | 0.7454 | 0.9227 | - | - | - | 930.75 | 2.33 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileViT_XS_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/MobileViT_XS_infer.tar) |
| MobileViT_S | 0.7814 | 0.9413 | - | - | - | 1849.35 | 5.59 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileViT_S_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/MobileViT_S_infer.tar) |
| MobileViTv2_x0_5 | 0.7017 | 0.8988 | - | - | - | 480.46 | 1.37 | [下载链接]() | [下载链接]() |
| MobileViTv2_x1_0 | 0.7813 | 0.9417 | - | - | - | 1843.81 | 4.90 | [下载链接]() | [下载链接]() |
| MobileViTv2_x1_5 | 0.8034 | 0.9509 | - | - | - | 4090.07 | 10.60 | [下载链接]() | [下载链接]() |
| MobileViTv2_x2_0 | 0.8116 | 0.9537 | - | - | - | 7219.23 | 18.45 | [下载链接]() | [下载链接]() |
| MobileViTV2_x0_5 | 0.7017 | 0.8988 | - | - | - | 480.46 | 1.37 | [下载链接]() | [下载链接]() |
| MobileViTV2_x1_0 | 0.7813 | 0.9417 | - | - | - | 1843.81 | 4.90 | [下载链接]() | [下载链接]() |
| MobileViTV2_x1_5 | 0.8034 | 0.9509 | - | - | - | 4090.07 | 10.60 | [下载链接]() | [下载链接]() |
| MobileViTV2_x2_0 | 0.8116 | 0.9537 | - | - | - | 7219.23 | 18.45 | [下载链接]() | [下载链接]() |
| MobileViTv3_XXS | 0.7087 | 0.8976 | - | - | - | 289.02 | 1.25 | [下载链接]() | [下载链接]() |
| MobileViTv3_XS | 0.7663 | 0.9332 | - | - | - | 926.98 | 2.49 | [下载链接]() | [下载链接]() |
| MobileViTv3_S | 0.7928 | 0.9454 | - | - | - | 1841.39 | 5.76 | [下载链接]() | [下载链接]() |
@ -924,8 +924,6 @@ TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE.
<a name="ref50">[50]</a>Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang, Li Dong, Furu Wei, Baining Guo. Swin Transformer V2: Scaling Up Capacity and Resolution
<<<<<<< HEAD
<a name="ref50">[51]</a>Wadekar, Shakti N. and Chaurasia, Abhishek. MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features
=======
<a name="ref51">[51]</a>Sachin Mehta and Mohammad Rastegari. Separable Self-attention for Mobile Vision Transformers
>>>>>>> add MobileViTv2
<a name="ref52">[52]</a>Wadekar, Shakti N. and Chaurasia, Abhishek. MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features

2
ppcls/arch/backbone/__init__.py
View File

@ -78,7 +78,7 @@ from .model_zoo.cae import cae_base_patch16_224, cae_large_patch16_224
from .model_zoo.cvt import CvT_13_224, CvT_13_384, CvT_21_224, CvT_21_384, CvT_W24_384
from .model_zoo.micronet import MicroNet_M0, MicroNet_M1, MicroNet_M2, MicroNet_M3
from .model_zoo.mobilenext import MobileNeXt_x0_35, MobileNeXt_x0_5, MobileNeXt_x0_75, MobileNeXt_x1_0, MobileNeXt_x1_4
from .model_zoo.mobilevit_v2 import MobileViTv2_x0_5, MobileViTv2_x0_75, MobileViTv2_x1_0, MobileViTv2_x1_25, MobileViTv2_x1_5, MobileViTv2_x1_75, MobileViTv2_x2_0
from .model_zoo.mobilevit_v2 import MobileViTV2_x0_5, MobileViTV2_x0_75, MobileViTV2_x1_0, MobileViTV2_x1_25, MobileViTV2_x1_5, MobileViTV2_x1_75, MobileViTV2_x2_0
from .model_zoo.mobilevit_v3 import MobileViTv3_XXS, MobileViTv3_XS, MobileViTv3_S, MobileViTv3_XXS_L2, MobileViTv3_XS_L2, MobileViTv3_S_L2, MobileViTv3_x0_5, MobileViTv3_x0_75, MobileViTv3_x1_0
from .variant_models.resnet_variant import ResNet50_last_stage_stride1

66
ppcls/arch/backbone/model_zoo/mobilevit_v2.py
View File

@ -25,13 +25,13 @@ import paddle.nn.functional as F
from ....utils.save_load import load_dygraph_pretrain, load_dygraph_pretrain_from_url
MODEL_URLS = {
"MobileViTv2_x0_5": "",
"MobileViTv2_x0_75": "",
"MobileViTv2_x1_0": "",
"MobileViTv2_x1_25": "",
"MobileViTv2_x1_5": "",
"MobileViTv2_x1_75": "",
"MobileViTv2_x2_0": "",
"MobileViTV2_x0_5": "",
"MobileViTV2_x0_75": "",
"MobileViTV2_x1_0": "",
"MobileViTV2_x1_25": "",
"MobileViTV2_x1_5": "",
"MobileViTV2_x1_75": "",
"MobileViTV2_x2_0": "",
}
layer_norm_2d = partial(nn.GroupNorm, num_groups=1)
@ -179,9 +179,9 @@ class LinearAttnFFN(nn.Layer):
return x
class MobileViTv2Block(nn.Layer):
class MobileViTV2Block(nn.Layer):
"""
This class defines the `MobileViTv2 block`
This class defines the `MobileViTV2 block`
"""
def __init__(self,
@ -302,9 +302,9 @@ class MobileViTv2Block(nn.Layer):
return fm
class MobileViTv2(nn.Layer):
class MobileViTV2(nn.Layer):
"""
MobileViTv2
MobileViTV2
"""
def __init__(self,
@ -415,7 +415,7 @@ class MobileViTv2(nn.Layer):
input_channel = cfg.get("out_channels")
block.append(
MobileViTv2Block(
MobileViTV2Block(
in_channels=input_channel,
attn_unit_dim=cfg["attn_unit_dim"],
ffn_multiplier=cfg.get("ffn_multiplier"),
@ -540,64 +540,64 @@ def get_configuration(width_multiplier) -> Dict:
return config
def MobileViTv2_x2_0(pretrained=False, use_ssld=False, **kwargs):
def MobileViTV2_x2_0(pretrained=False, use_ssld=False, **kwargs):
width_multiplier = 2.0
model = MobileViTv2(get_configuration(width_multiplier), **kwargs)
model = MobileViTV2(get_configuration(width_multiplier), **kwargs)
_load_pretrained(
pretrained, model, MODEL_URLS["MobileViTv2_x2_0"], use_ssld=use_ssld)
pretrained, model, MODEL_URLS["MobileViTV2_x2_0"], use_ssld=use_ssld)
return model
def MobileViTv2_x1_75(pretrained=False, use_ssld=False, **kwargs):
def MobileViTV2_x1_75(pretrained=False, use_ssld=False, **kwargs):
width_multiplier = 1.75
model = MobileViTv2(get_configuration(width_multiplier), **kwargs)
model = MobileViTV2(get_configuration(width_multiplier), **kwargs)
_load_pretrained(
pretrained, model, MODEL_URLS["MobileViTv2_x1_75"], use_ssld=use_ssld)
pretrained, model, MODEL_URLS["MobileViTV2_x1_75"], use_ssld=use_ssld)
return model
def MobileViTv2_x1_5(pretrained=False, use_ssld=False, **kwargs):
def MobileViTV2_x1_5(pretrained=False, use_ssld=False, **kwargs):
width_multiplier = 1.5
model = MobileViTv2(get_configuration(width_multiplier), **kwargs)
model = MobileViTV2(get_configuration(width_multiplier), **kwargs)
_load_pretrained(
pretrained, model, MODEL_URLS["MobileViTv2_x1_5"], use_ssld=use_ssld)
pretrained, model, MODEL_URLS["MobileViTV2_x1_5"], use_ssld=use_ssld)
return model
def MobileViTv2_x1_25(pretrained=False, use_ssld=False, **kwargs):
def MobileViTV2_x1_25(pretrained=False, use_ssld=False, **kwargs):
width_multiplier = 1.25
model = MobileViTv2(get_configuration(width_multiplier), **kwargs)
model = MobileViTV2(get_configuration(width_multiplier), **kwargs)
_load_pretrained(
pretrained, model, MODEL_URLS["MobileViTv2_x1_25"], use_ssld=use_ssld)
pretrained, model, MODEL_URLS["MobileViTV2_x1_25"], use_ssld=use_ssld)
return model
def MobileViTv2_x1_0(pretrained=False, use_ssld=False, **kwargs):
def MobileViTV2_x1_0(pretrained=False, use_ssld=False, **kwargs):
width_multiplier = 1.0
model = MobileViTv2(get_configuration(width_multiplier), **kwargs)
model = MobileViTV2(get_configuration(width_multiplier), **kwargs)
_load_pretrained(
pretrained, model, MODEL_URLS["MobileViTv2_x1_0"], use_ssld=use_ssld)
pretrained, model, MODEL_URLS["MobileViTV2_x1_0"], use_ssld=use_ssld)
return model
def MobileViTv2_x0_75(pretrained=False, use_ssld=False, **kwargs):
def MobileViTV2_x0_75(pretrained=False, use_ssld=False, **kwargs):
width_multiplier = 0.75
model = MobileViTv2(get_configuration(width_multiplier), **kwargs)
model = MobileViTV2(get_configuration(width_multiplier), **kwargs)
_load_pretrained(
pretrained, model, MODEL_URLS["MobileViTv2_x0_75"], use_ssld=use_ssld)
pretrained, model, MODEL_URLS["MobileViTV2_x0_75"], use_ssld=use_ssld)
return model
def MobileViTv2_x0_5(pretrained=False, use_ssld=False, **kwargs):
def MobileViTV2_x0_5(pretrained=False, use_ssld=False, **kwargs):
width_multiplier = 0.5
model = MobileViTv2(get_configuration(width_multiplier), **kwargs)
model = MobileViTV2(get_configuration(width_multiplier), **kwargs)
_load_pretrained(
pretrained, model, MODEL_URLS["MobileViTv2_x0_5"], use_ssld=use_ssld)
pretrained, model, MODEL_URLS["MobileViTV2_x0_5"], use_ssld=use_ssld)
return model

2
ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x0_5.yaml → ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x0_5.yaml
View File

@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv2_x0_5
name: MobileViTV2_x0_5
class_num: 1000
# loss function config for traing/eval process

2
ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x1_0.yaml → ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x1_0.yaml
View File

@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv2_x1_0
name: MobileViTV2_x1_0
class_num: 1000
# loss function config for traing/eval process

2
ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x1_5.yaml → ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x1_5.yaml
View File

@ -29,7 +29,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv2_x1_5
name: MobileViTV2_x1_5
class_num: 1000
# loss function config for traing/eval process

2
ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x2_0.yaml → ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x2_0.yaml
View File

@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv2_x2_0
name: MobileViTV2_x2_0
class_num: 1000
# loss function config for traing/eval process

2
ppcls/data/preprocess/ops/randaugment.py
View File

@ -264,7 +264,7 @@ class RandAugmentV2(RandAugment):
class RandAugmentV3(RandAugment):
"""Customed RandAugment for MobileViTv2"""
"""Customed RandAugment for MobileViTV2"""
def __init__(self,
num_layers=2,

8
test_tipc/configs/MobileViTv2/MobileViTv2_x1_0_train_infer_python.txt → test_tipc/configs/MobileViTV2/MobileViTV2_x0_5_train_infer_python.txt
View File

@ -1,5 +1,5 @@
===========================train_params===========================
model_name:MobileViTv2_x1_0
model_name:MobileViTV2_x0_5
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x1_0.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x0_5.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x1_0.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x0_5.yaml
quant_export:null
fpgm_export:null
distill_export:null

8
test_tipc/configs/MobileViTv2/MobileViTv2_x1_5_train_infer_python.txt → test_tipc/configs/MobileViTV2/MobileViTV2_x1_0_train_infer_python.txt
View File

@ -1,5 +1,5 @@
===========================train_params===========================
model_name:MobileViTv2_x1_5
model_name:MobileViTV2_x1_0
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x1_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x1_5.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x1_0.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x1_5.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x1_0.yaml
quant_export:null
fpgm_export:null
distill_export:null

8
test_tipc/configs/MobileViTv2/MobileViTv2_x2_0_train_infer_python.txt → test_tipc/configs/MobileViTV2/MobileViTV2_x1_5_train_infer_python.txt
View File

@ -1,5 +1,5 @@
===========================train_params===========================
model_name:MobileViTv2_x2_0
model_name:MobileViTV2_x1_5
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x2_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x1_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x2_0.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x1_5.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x2_0.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x1_5.yaml
quant_export:null
fpgm_export:null
distill_export:null

8
test_tipc/configs/MobileViTv2/MobileViTv2_x0_5_train_infer_python.txt → test_tipc/configs/MobileViTV2/MobileViTV2_x2_0_train_infer_python.txt
View File

@ -1,5 +1,5 @@
===========================train_params===========================
model_name:MobileViTv2_x0_5
model_name:MobileViTV2_x2_0
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x2_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x0_5.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x2_0.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv2/MobileViTv2_x0_5.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV2/MobileViTV2_x2_0.yaml
quant_export:null
fpgm_export:null
distill_export:null