Skip to content

Commit

Permalink
Merge pull request PaddlePaddle#1120 from FlyingQianMM/v2.0.0_qh
Browse files Browse the repository at this point in the history
rename develop to release 2.0.0
  • Loading branch information
FlyingQianMM authored Sep 10, 2021
2 parents 0bf64dd + 5ff04d6 commit c9e7e11
Show file tree
Hide file tree
Showing 54 changed files with 205 additions and 195 deletions.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@

### 发布产业实践案例:钢筋计数、缺陷检测、机械手抓取、工业表计读数、Windows系统下使用C#语言部署。[欢迎体验](./examples)

### 升级PaddleX GUI,支持30系列显卡、新增模型PP-YOLO V2、PP-YOLO Tiny 、BiSeNetV2,新增导出API训练脚本功能,无缝切换PaddleX API训练。[欢迎体验](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/install.md#2-padldex-gui%E5%BC%80%E5%8F%91%E6%A8%A1%E5%BC%8F%E5%AE%89%E8%A3%85)
### 升级PaddleX GUI,支持30系列显卡、新增模型PP-YOLO V2、PP-YOLO Tiny 、BiSeNetV2,新增导出API训练脚本功能,无缝切换PaddleX API训练。[欢迎体验](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/install.md#2-padldex-gui%E5%BC%80%E5%8F%91%E6%A8%A1%E5%BC%8F%E5%AE%89%E8%A3%85)

[![License](https://img.shields.io/badge/license-Apache%202-red.svg)](LICENSE) [![Version](https://img.shields.io/github/release/PaddlePaddle/PaddleX.svg)](https://github.com/PaddlePaddle/PaddleX/releases) ![python version](https://img.shields.io/badge/python-3.6+-orange.svg) ![support os](https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-yellow.svg)
![QQGroup](https://img.shields.io/badge/QQ_Group-1045148026-52B6EF?style=social&logo=tencent-qq&logoColor=000&logoWidth=20)
Expand Down
3 changes: 2 additions & 1 deletion deploy/cpp/docs/compile/openvino/openvino_linux.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

本文档指引用户如何基于OpenVINO对飞桨模型进行推理,并编译执行。进行以下编译操作前请先安装好OpenVINO,OpenVINO安装请参考官网[OpenVINO-Linux](https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_linux.html)

**注意:**
**注意:**

- 我们测试的openvino版本为2021.3,如果你使用其它版本遇到问题,可以尝试切换到该版本
- 当前检测模型转换为openvino格式是有问题的,暂时只支持分割和分类模型
Expand Down Expand Up @@ -66,6 +66,7 @@ resnet50
### Step 1. 获取部署代码
```
git clone https://github.com/PaddlePaddle/PaddleX.git
git checkout release/2.0.0
cd PaddleX/deploy/cpp
```
**说明**`C++`预测代码在`PaddleX/deploy/cpp` 目录,该目录不依赖任何`PaddleX`下其他目录。所有的推理实现代码在`model_deploy`目录下,所有示例代码都在`demo`目录下,script目录为编译脚本。
Expand Down
2 changes: 2 additions & 0 deletions deploy/cpp/docs/compile/openvino/openvino_windows.md
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,8 @@ resnet50
### Step 1. 获取部署代码
```
git clone https://github.com/PaddlePaddle/PaddleX.git
cd PaddleX
git checkout release/2.0.0
```
**说明**`C++`预测代码在`PaddleX/deploy/cpp` 目录,该目录不依赖任何`PaddleX`下其他目录。所有的推理实现代码在`model_deploy`目录下,所有示例代码都在`demo`目录下。

Expand Down
4 changes: 3 additions & 1 deletion deploy/cpp/docs/compile/paddle/linux.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,9 @@ Ubuntu 16.04/18.04
### Step1: 获取部署代码
```
git clone https://github.com/PaddlePaddle/PaddleX.git
cd PaddleX/deploy/cpp
cd PaddleX/
git checkout release/2.0.0
cd deploy/cpp
```
**说明**`C++`预测代码在`PaddleX/deploy/cpp` 目录,该目录不依赖任何`PaddleX`下其他目录。所有的公共实现代码在`model_deploy`目录下,所有示例代码都在`demo`目录下。

Expand Down
2 changes: 2 additions & 0 deletions deploy/cpp/docs/compile/paddle/windows.md
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@ d:
mkdir projects
cd projects
git clone https://github.com/PaddlePaddle/PaddleX.git
cd PaddleX
git checkout release/2.0.0
```

**说明**:其中`C++`预测代码在`PaddleX\dygraph\deploy\cpp` 目录,该目录不依赖任何`PaddleX`下其他目录。所有的公共实现代码在`model_deploy`目录下,所有示例代码都在`demo`目录下。
Expand Down
2 changes: 1 addition & 1 deletion deploy/cpp/docs/compile/tensorrt/trt.md
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ $ docker run -it --gpus=all --name tensorrt-onnx -v ~/paddle2onnx/:/paddle2onnx
```
$ git clone https://github.com/PaddlePaddle/PaddleX.git
$ cd PaddleX
$ git checkout deploykit
$ git checkout release/2.0.0
$ cd deploy/cpp
$ git clone https://github.com/NVIDIA/TensorRT.git
# 如果不是其他版本的容器, 将cuda_dir路径换成自己的cuda路径即可
Expand Down
2 changes: 1 addition & 1 deletion deploy/cpp/docs/compile/triton/docker.md
Original file line number Diff line number Diff line change
Expand Up @@ -168,7 +168,7 @@ curl -v localhost:8000/v2/health/ready
```
git clone https://github.com/PaddlePaddle/PaddleX.git
cd PaddleX
git checkout deploykit
git checkout release/2.0.0
```

### 3.2 启动Triton客户端容器
Expand Down
8 changes: 4 additions & 4 deletions docs/CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -18,10 +18,10 @@

- **2021.07.06 v2.0.0-rc3**

* PaddleX部署全面升级,支持飞桨视觉套件PaddleDetection、PaddleClas、PaddleSeg、PaddleX的端到端统一部署能力。[使用教程](https://github.com/PaddlePaddle/PaddleX/tree/develop/deploy/cpp)
* 全新发布Manufacture SDK,提供工业级多端多平台部署加速的预编译飞桨部署开发包(SDK),通过配置业务逻辑流程文件即可以低代码方式快速完成推理部署。[使用教程](https://github.com/PaddlePaddle/PaddleX/tree/develop/deploy/cpp/docs/manufacture_sdk)
* 发布产业实践案例:钢筋计数、缺陷检测、机械手抓取、工业表计读数、Windows系统下使用C#语言部署。[使用教程](https://github.com/PaddlePaddle/PaddleX/tree/develop/examples)
* 升级PaddleX GUI,支持30系列显卡、新增模型PP-YOLO V2、PP-YOLO Tiny 、BiSeNetV2。[使用教程](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/install.md#2-padldex-gui%E5%BC%80%E5%8F%91%E6%A8%A1%E5%BC%8F%E5%AE%89%E8%A3%85)
* PaddleX部署全面升级,支持飞桨视觉套件PaddleDetection、PaddleClas、PaddleSeg、PaddleX的端到端统一部署能力。[使用教程](https://github.com/PaddlePaddle/PaddleX/tree/release/2.0.0/deploy/cpp)
* 全新发布Manufacture SDK,提供工业级多端多平台部署加速的预编译飞桨部署开发包(SDK),通过配置业务逻辑流程文件即可以低代码方式快速完成推理部署。[使用教程](https://github.com/PaddlePaddle/PaddleX/tree/release/2.0.0/deploy/cpp/docs/manufacture_sdk)
* 发布产业实践案例:钢筋计数、缺陷检测、机械手抓取、工业表计读数、Windows系统下使用C#语言部署。[使用教程](https://github.com/PaddlePaddle/PaddleX/tree/release/2.0.0/examples)
* 升级PaddleX GUI,支持30系列显卡、新增模型PP-YOLO V2、PP-YOLO Tiny 、BiSeNetV2。[使用教程](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/install.md#2-padldex-gui%E5%BC%80%E5%8F%91%E6%A8%A1%E5%BC%8F%E5%AE%89%E8%A3%85)


- **2021.05.19 v2.0.0-rc**
Expand Down
2 changes: 1 addition & 1 deletion docs/FAQ/FAQ.md
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@

**Q:** 预测结果如何可视化?

**A:** 检测结果可以用`pdx.det.visualize`,分割结果可以用`pdx.seg.visualize`,API说明见[文档](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/prediction.md)
**A:** 检测结果可以用`pdx.det.visualize`,分割结果可以用`pdx.seg.visualize`,API说明见[文档](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/prediction.md)


**Q:** 如何用旧的部署代码部署新的模型?
Expand Down
28 changes: 14 additions & 14 deletions docs/apis/datasets.md
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ paddlex.datasets.ImageNet(data_dir, file_list, label_list, transforms=None, num_
```
读取ImageNet格式的分类数据集,并对样本进行相应的处理。ImageNet数据集格式的介绍可查看文档:[数据集格式说明](../data/format/classification.md)

示例:[代码文件](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/image_classification/mobilenetv3_small.py)
示例:[代码文件](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/tutorials/train/image_classification/mobilenetv3_small.py)

> **参数**
>
Expand All @@ -35,7 +35,7 @@ paddlex.datasets.VOCDetection(data_dir, file_list, label_list, transforms=None,

> 读取PascalVOC格式的检测数据集,并对样本进行相应的处理。PascalVOC数据集格式的介绍可查看文档:[数据集格式说明](../data/format/detection.md)
> 示例:[代码文件](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/object_detection/yolov3_darknet53.py)
> 示例:[代码文件](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/tutorials/train/object_detection/yolov3_darknet53.py)
> **参数**
>
Expand Down Expand Up @@ -80,7 +80,7 @@ dataset = 'https://bj.bcebos.com/paddlex/datasets/insect_det.tar.gz'
pdx.utils.download_and_decompress(dataset, path='./')

# 定义训练和验证时的transforms
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/transforms/transforms.md
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/transforms/transforms.md
train_transforms = T.Compose([
T.MixupImage(mixup_epoch=-1), T.RandomDistort(),
T.RandomExpand(im_padding_value=[123.675, 116.28, 103.53]), T.RandomCrop(),
Expand All @@ -97,7 +97,7 @@ eval_transforms = T.Compose([
])

# 定义训练和验证所用的数据集
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/datasets.md
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/datasets.md
train_dataset = pdx.datasets.VOCDetection(
data_dir='insect_det',
file_list='insect_det/train_list.txt',
Expand All @@ -117,15 +117,15 @@ anchors = train_dataset.cluster_yolo_anchor(num_anchors=9, image_size=608)
anchor_masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]

# 初始化模型,并进行训练
# 可使用VisualDL查看训练指标,参考https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/train/visualdl.md
# 可使用VisualDL查看训练指标,参考https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/train/visualdl.md
num_classes = len(train_dataset.labels)
model = pdx.det.PPYOLO(num_classes=num_classes,
backbone='ResNet50_vd_dcn',
anchors=anchors,
anchor_masks=anchor_masks)

# API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/models/detection.md
# 各参数介绍与调整说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/parameters.md
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/models/detection.md
# 各参数介绍与调整说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/parameters.md
model.train(
num_epochs=200,
train_dataset=train_dataset,
Expand All @@ -149,7 +149,7 @@ paddlex.datasets.CocoDetection(data_dir, ann_file, transforms=None, num_workers=

> 读取MSCOCO格式的检测数据集,并对样本进行相应的处理,该格式的数据集同样可以应用到实例分割模型的训练中。MSCOCO数据集格式的介绍可查看文档:[数据集格式说明](../data/format/instance_segmentation.md)
> 示例:[代码文件](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/instance_segmentation/mask_rcnn_r50_fpn.py)
> 示例:[代码文件](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/tutorials/train/instance_segmentation/mask_rcnn_r50_fpn.py)
> **参数**
>
Expand Down Expand Up @@ -193,7 +193,7 @@ dataset = 'https://bj.bcebos.com/paddlex/datasets/insect_det.tar.gz'
pdx.utils.download_and_decompress(dataset, path='./')

# 定义训练和验证时的transforms
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/transforms/transforms.md
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/transforms/transforms.md
train_transforms = T.Compose([
T.MixupImage(mixup_epoch=-1), T.RandomDistort(),
T.RandomExpand(im_padding_value=[123.675, 116.28, 103.53]), T.RandomCrop(),
Expand All @@ -210,7 +210,7 @@ eval_transforms = T.Compose([
])

# 定义训练和验证所用的数据集
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/datasets.md
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/datasets.md
train_dataset = pdx.datasets.CocoDetection(
data_dir='xiaoduxiong_ins_det/JPEGImages',
ann_file='xiaoduxiong_ins_det/train.json',
Expand All @@ -226,15 +226,15 @@ anchors = train_dataset.cluster_yolo_anchor(num_anchors=9, image_size=608)
anchor_masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]

# 初始化模型,并进行训练
# 可使用VisualDL查看训练指标,参考https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/train/visualdl.md
# 可使用VisualDL查看训练指标,参考https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/train/visualdl.md
num_classes = len(train_dataset.labels)
model = pdx.det.PPYOLO(num_classes=num_classes,
backbone='ResNet50_vd_dcn',
anchors=anchors,
anchor_masks=anchor_masks)

# API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/models/detection.md
# 各参数介绍与调整说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/parameters.md
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/models/detection.md
# 各参数介绍与调整说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/parameters.md
model.train(
num_epochs=200,
train_dataset=train_dataset,
Expand All @@ -258,7 +258,7 @@ paddlex.datasets.SegDataset(data_dir, file_list, label_list=None, transforms=Non

> 读取语义分割任务数据集,并对样本进行相应的处理。语义分割任务数据集格式的介绍可查看文档:[数据集格式说明](../data/format/segmentation.md)
> 示例:[代码文件](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/semantic_segmentation/unet.py)
> 示例:[代码文件](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/tutorials/train/semantic_segmentation/unet.py)
> **参数**
>
Expand Down
2 changes: 1 addition & 1 deletion docs/apis/export_model.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

**注:所有涉及到模型部署,均需要参考本文档,进行部署模型导出**

在服务端部署模型时需要将训练过程中保存的模型导出为inference格式模型,导出的inference格式模型包括`model.pdmodel``model.pdiparams``model.pdiparams.info``model.yml``pipeline.yml`五个文件,分别表示模型的网络结构、模型权重、模型权重名称、模型的配置文件(包括数据预处理参数等)和可用于[PaddleX Manufacture SDK](https://github.com/PaddlePaddle/PaddleX/tree/develop/deploy/cpp/docs/manufacture_sdk)的流程配置文件。
在服务端部署模型时需要将训练过程中保存的模型导出为inference格式模型,导出的inference格式模型包括`model.pdmodel``model.pdiparams``model.pdiparams.info``model.yml``pipeline.yml`五个文件,分别表示模型的网络结构、模型权重、模型权重名称、模型的配置文件(包括数据预处理参数等)和可用于[PaddleX Manufacture SDK](https://github.com/PaddlePaddle/PaddleX/tree/release/2.0.0/deploy/cpp/docs/manufacture_sdk)的流程配置文件。

> **检查你的模型文件夹**,如果里面是`model.pdparams``model.pdopt``model.yml`3个文件时,那么就需要按照下面流程进行模型导出
Expand Down
6 changes: 3 additions & 3 deletions docs/apis/prediction.md
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ result = model.predict(test_jpg)
pdx.det.visualize(test_jpg, result, threshold=0.3, save_dir='./')
```
- YOLOv3模型predict接口[说明文档](./apis/models/detection.md#predict)
- 可视化pdx.det.visualize接口[说明文档](https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/cv/models/utils/visualize.py#L25)
- 可视化pdx.det.visualize接口[说明文档](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/paddlex/cv/models/utils/visualize.py#L25)
> 注意:目标检测和实例分割模型在调用`predict`接口得到的结果需用户自行过滤低置信度结果,在`paddlex.det.visualize`接口中,我们提供了`threshold`用于过滤,置信度低于此值的结果将被过滤,不会可视化。
![](./images/yolo_predict.jpg)

Expand All @@ -58,7 +58,7 @@ result = model.predict(test_jpg)
pdx.det.visualize(test_jpg, result, threshold=0.5, save_dir='./')
```
- MaskRCNN模型predict接口[说明文档](./apis/models/instance_segmentation.md#predict)
- 可视化pdx.det.visualize接口[说明文档](https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/cv/models/utils/visualize.py#L25)
- 可视化pdx.det.visualize接口[说明文档](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/paddlex/cv/models/utils/visualize.py#L25)

**注意**:目标检测和实例分割模型在调用`predict`接口得到的结果需用户自行过滤低置信度结果,在`paddlex.det.visualize`接口中,我们提供了`threshold`用于过滤,置信度低于此值的结果将被过滤,不会可视化。
![](./images/mask_predict.jpg)
Expand All @@ -78,5 +78,5 @@ pdx.seg.visualize(test_jpg, result, weight=0.0, save_dir='./')
在上述示例代码中,通过调用`paddlex.seg.visualize`可以对语义分割的预测结果进行可视化,可视化的结果保存在`save_dir`下,见下图。其中`weight`参数用于调整预测结果和原图结果融合展现时的权重,0.0时只展示预测结果mask的可视化,1.0时只展示原图可视化。

- DeepLabv3模型predict接口[说明文档](./apis/models/semantic_segmentation.md#predict)
- 可视化pdx.seg.visualize接口[说明文档](https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/cv/models/utils/visualize.py#L50)
- 可视化pdx.seg.visualize接口[说明文档](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/paddlex/cv/models/utils/visualize.py#L50)
![](images/deeplab_predict.jpg)
10 changes: 5 additions & 5 deletions docs/apis/tools/anchor_clustering.md
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ dataset = 'https://bj.bcebos.com/paddlex/datasets/insect_det.tar.gz'
pdx.utils.download_and_decompress(dataset, path='./')

# 定义训练和验证时的transforms
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/transforms/transforms.md
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/transforms/transforms.md
train_transforms = T.Compose([
T.MixupImage(mixup_epoch=-1), T.RandomDistort(),
T.RandomExpand(im_padding_value=[123.675, 116.28, 103.53]), T.RandomCrop(),
Expand All @@ -52,7 +52,7 @@ eval_transforms = T.Compose([
])

# 定义训练和验证所用的数据集
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/datasets.md
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/datasets.md
train_dataset = pdx.datasets.VOCDetection(
data_dir='insect_det',
file_list='insect_det/train_list.txt',
Expand All @@ -75,15 +75,15 @@ anchors = cluster()
anchor_masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]

# 初始化模型,并进行训练
# 可使用VisualDL查看训练指标,参考https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/train/visualdl.md
# 可使用VisualDL查看训练指标,参考https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/train/visualdl.md
num_classes = len(train_dataset.labels)
model = pdx.det.PPYOLO(num_classes=num_classes,
backbone='ResNet50_vd_dcn',
anchors=anchors,
anchor_masks=anchor_masks)

# API说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/apis/models/detection.md
# 各参数介绍与调整说明:https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/parameters.md
# API说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/apis/models/detection.md
# 各参数介绍与调整说明:https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/docs/parameters.md
model.train(
num_epochs=200,
train_dataset=train_dataset,
Expand Down
2 changes: 1 addition & 1 deletion docs/apis/transforms/transforms.md
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
paddlex.transforms.Compose(transforms)
```

根据数据预处理/增强算子对输入数据进行操作。 [使用示例](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/image_classification/mobilenetv3_small.py#L10)
根据数据预处理/增强算子对输入数据进行操作。 [使用示例](https://github.com/PaddlePaddle/PaddleX/blob/release/2.0.0/tutorials/train/image_classification/mobilenetv3_small.py#L10)

> **参数**
> * **transforms** (List[paddlex.transforms.Transform]): 数据预处理/数据增强列表。
Expand Down
Loading

0 comments on commit c9e7e11

Please sign in to comment.