diff --git a/docs/en/inference_deployment/cpp_deploy_on_windows_en.md b/docs/en/inference_deployment/cpp_deploy_on_windows_en.md deleted file mode 100755 index 6e2b37038e104275d16ea40e41320d2e7793af19..0000000000000000000000000000000000000000 --- a/docs/en/inference_deployment/cpp_deploy_on_windows_en.md +++ /dev/null @@ -1,119 +0,0 @@ -# Visual Studio 2019 Community CMake 编译指南 - -PaddleClas在Windows 平台下基于`Visual Studio 2019 Community` 进行了测试。微软从`Visual Studio 2017`开始即支持直接管理`CMake`跨平台编译项目，但是直到`2019`才提供了稳定和完全的支持，所以如果你想使用CMake管理项目编译构建，我们推荐使用`Visual Studio 2019`。如果您希望通过生成`sln解决方案`的方式进行编译，可以参考该文档：[https://zhuanlan.zhihu.com/p/145446681](https://zhuanlan.zhihu.com/p/145446681)。 - - -## 前置条件 -* Visual Studio 2019 -* CUDA 9.0 / CUDA 10.0，cudnn 7.6+ （仅在使用GPU版本的预测库时需要） -* CMake 3.0+ - -请确保系统已经正确安装并配置好上述基本软件，其中： - * 在安装`Visual Studio 2019`时，`工作负载`需要勾选`使用C++的桌面开发`； - * CUDA需要正确安装并设置系统环境变量； - * CMake需要正确安装并将路径添加到系统环境变量中。 - -以下测试基于`Visual Studio 2019 Community`版本。 - -**下面所有示例以工作目录为 `D:\projects`演示**。 - -### Step1: 下载PaddlePaddle C++ 预测库 paddle_inference_install_dir - -PaddlePaddle C++ 预测库针对不同的`CPU`和`CUDA`版本提供了不同的预编译版本，请根据实际情况下载: [C++预测库下载列表](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/guides/05_inference_deployment/inference/windows_cpp_inference.html)。 - -解压后`D:\projects\paddle_inference_install_dir`目录包含内容为： - -``` -paddle_inference_install_dir -├── paddle # paddle核心库和头文件 -| -├── third_party # 第三方依赖库和头文件 -| -└── version.txt # 版本和编译信息 -``` - -然后需要将`Paddle预测库`的路径`D:\projects\paddle_inference_install_dir\paddle\lib`添加到系统环境变量`Path`中。 - -### Step2: 安装配置OpenCV - -1. 在OpenCV官网下载适用于Windows平台的3.4.6版本， [下载地址](https://sourceforge.net/projects/opencvlibrary/files/3.4.6/opencv-3.4.6-vc14_vc15.exe/download) -2. 运行下载的可执行文件，将OpenCV解压至指定目录，如`D:\projects\opencv` -3. 配置环境变量，如下流程所示 - - 此电脑（我的电脑）-> 属性 -> 高级系统设置 -> 环境变量 - - 在系统变量中找到Path（如没有，自行创建），并双击编辑 - - 新建，将OpenCV路径填入并保存，如 `D:\projects\opencv\build\x64\vc14\bin` - -### Step3: 使用Visual Studio 2019直接编译CMake - -1. 打开Visual Studio 2019 Community，点击 `继续但无需代码` - -![step2](./imgs/vs2019_step1.png) - -2. 点击： `文件`->`打开`->`CMake` - -![step2.1](./imgs/vs2019_step2.png) - -选择项目代码所在路径，并打开`CMakeList.txt`： - -![step2.2](./imgs/vs2019_step3.png) - -3. 点击：`项目`->`cpp_inference_demo的CMake设置` - -![step3](./imgs/vs2019_step4.png) - -4. 请设置以下参数的值 - - -| 名称 | 值 | 保存到 JSON | -| ----------------------------- | ------------------ | ----------- | -| CMAKE_BACKWARDS_COMPATIBILITY | 3.17 | [√] | -| CMAKE_BUILD_TYPE | RelWithDebInfo | [√] | -| CUDA_LIB | CUDA的库路径 | [√] | -| CUDNN_LIB | CUDNN的库路径 | [√] | -| OpenCV_DIR | OpenCV的安装路径 | [√] | -| PADDLE_LIB | Paddle预测库的路径 | [√] | -| WITH_GPU | [√] | [√] | -| WITH_MKL | [√] | [√] | -| WITH_STATIC_LIB | [√] | [√] | - -**注意**： - -1. `CMAKE_BACKWARDS_COMPATIBILITY` 的值请根据自己 `cmake` 版本设置，`cmake` 版本可以通过命令：`cmake --version` 查询； -2. `CUDA_LIB` 、 `CUDNN_LIB` 的值仅需在使用**GPU版本**预测库时指定，其中CUDA库版本尽量对齐，**使用9.0、10.0版本，不使用9.2、10.1等版本CUDA库**； -3. 在设置 `CUDA_LIB`、`CUDNN_LIB`、`OPENCV_DIR`、`PADDLE_LIB` 时，点击 `浏览`，分别设置相应的路径； - * `CUDA_LIB`和`CUDNN_LIB`：该路径取决于CUDA与CUDNN的安装位置。 - * `OpenCV_DIR`：该路径下需要有`.cmake`文件，一般为`opencv/build/`； - * `PADDLE_LIB`：该路径下需要有`CMakeCache.txt`文件，一般为`paddle_inference_install_dir/`。 -4. 在使用 `CPU` 版预测库时，请不要勾选 `WITH_GPU` - `保存到 JSON`。 - -![step4](./imgs/vs2019_step5.png) - -**设置完成后**, 点击上图中 `保存并生成CMake缓存以加载变量` 。 - -5. 点击`生成`->`全部生成` - -![step6](./imgs/vs2019_step6.png) - - -### Step4: 预测及可视化 - -在完成上述操作后，`Visual Studio 2019` 编译产出的可执行文件 `clas_system.exe` 在 `out\build\x64-Release`目录下，打开`cmd`，并切换到该目录： - -``` -cd D:\projects\PaddleClas\deploy\cpp_infer\out\build\x64-Release -``` -可执行文件`clas_system.exe`即为编译产出的的预测程序，其使用方法如下： - -```shell -.\clas_system.exe D:\projects\PaddleClas\deploy\cpp_infer\tools\config.txt .\docs\ILSVRC2012_val_00008306.JPEG -``` - -上述命令中，第一个参数（`D:\projects\PaddleClas\deploy\cpp_infer\tools\config.txt`）为配置文件路径，第二个参数（`.\docs\ILSVRC2012_val_00008306.JPEG`）为需要预测的图片路径。 - -注意，需要在配置文件中正确设置预测参数，包括所用模型文件的路径（`cls_model_path`和`cls_params_path`）。 - - -### 注意 -* 在Windows下的终端中执行文件exe时，可能会发生乱码的现象，此时需要在终端中输入`CHCP 65001`，将终端的编码方式由GBK编码(默认)改为UTF-8编码，更加具体的解释可以参考这篇博客：[https://blog.csdn.net/qq_35038153/article/details/78430359](https://blog.csdn.net/qq_35038153/article/details/78430359)。 -* 如果需要使用CPU预测，PaddlePaddle在Windows上仅支持avx的CPU预测，目前不支持noavx的CPU预测。 -* 在使用生成的`clas_system.exe`进行预测时，如提示`由于找不到paddle_fluid.dll，无法继续执行代码。重新安装程序可能会解决此问题`，请检查是否将Paddle预测库路径添加到系统环境变量，详见[Step1: 下载PaddlePaddle C++ 预测库 paddle_inference_install_dir](#step1-下载paddlepaddle-c-预测库-paddle_inference_install_dir) diff --git a/docs/en/inference_deployment/export_model_en.md b/docs/en/inference_deployment/export_model_en.md index 1cce541c3965d644b671d6b94aad3d9a2dd53b8b..9bc4fffd1f40fac23ea9cd715881df9f1bf39396 100644 --- a/docs/en/inference_deployment/export_model_en.md +++ b/docs/en/inference_deployment/export_model_en.md @@ -6,19 +6,21 @@ PaddlePaddle supports exporting inference model for deployment. Compared with tr ## Contents -- [1. 环境准备](#1) -- [2. 分类模型导出](#2) -- [3. 主体检测模型导出](#3) -- [4. 识别模型导出](#4) -- [5. 命令参数说明](#5) +- [1. Environmental preparation](#1) +- [2. Export classification model](#2) +- [3. Export mainbody detection model](#3) +- [4. Export recognition model](#4) +- [5. Parameter description](#5) + ## 1. Environmental preparation First, refer to the [Installing PaddlePaddle](../installation/install_paddle_en.md) and the [Installing PaddleClas](../installation/install_paddleclas_en.md) to prepare environment. + ## 2. Export classification model Change the working directory to PaddleClas: @@ -43,11 +45,13 @@ python tools/export_model.py ``` + ## 3. Export mainbody detection model About exporting mainbody detection model in details, please refer[mainbody detection](../image_recognition_pipeline/mainbody_detection_en.md). + ## 4. Export recognition model Change the working directory to PaddleClas: @@ -74,6 +78,7 @@ python3 tools/export_model.py \ Notice, the inference model exported by above command is truncated on embedding layer, so the output of the model is n-dimensional embedding feature. + ## 5. Parameter description In the above model export command, the configuration file used must be the same as the training configuration file. The following fields in the configuration file are used to configure exporting model parameters. diff --git a/docs/en/others/train_with_DALI_en.md b/docs/en/others/train_with_DALI_en.md index a67a76166b0d890d69f5e2a8cd14c68b146c785b..384a81623171c32b4ec49f1b5aa22f4f5b0b61e8 100644 --- a/docs/en/others/train_with_DALI_en.md +++ b/docs/en/others/train_with_DALI_en.md @@ -1,11 +1,25 @@ # Train with DALI -## Preface -[The NVIDIA Data Loading Library](https://docs.nvidia.com/deeplearning/dali/user-guide/docs/index.html) (DALI) is a library for data loading and pre-processing to accelerate deep learning applications. It can build Dataloader of Paddle. +--- -Since the Deep learning relies on a large amount of data in the training stage, these data need to be loaded and preprocessed. These operations are usually executed on the CPU, which limits the further improvement of the training speed, especially when the batch_size is large, which become the bottleneck of speed. DALI can use GPU to accelerate these operations, thereby further improve the training speed. +## Contents +* [1. Preface](#1) +* [2. Installing DALI](#2) +* [3. Using DALI](#3) +* [4. Train with FP16](#4) + + + +## 1. Preface + +[The NVIDIA Data Loading Library](https://docs.nvidia.com/deeplearning/dali/user-guide/docs/index.html) (DALI) is a library for data loading and pre-processing to accelerate deep learning applications. It can build Dataloader of PaddlePaddle. + +Since the Deep Learning relies on a large amount of data in the training stage, these data need to be loaded and preprocessed. These operations are usually executed on the CPU, which limits the further improvement of the training speed, especially when the batch_size is large, which become the bottleneck of training speed. DALI can use GPU to accelerate these operations, thereby further improve the training speed. + + + +## 2. Installing DALI -## Installing DALI DALI only support Linux x64 and version of CUDA is 10.2 or later. * For CUDA 10: @@ -18,45 +32,47 @@ DALI only support Linux x64 and version of CUDA is 10.2 or later. For more information about installing DALI, please refer to [DALI](https://docs.nvidia.com/deeplearning/dali/user-guide/docs/installation.html). -## Using DALI -Paddleclas supports training with DALI in static graph. Since DALI only supports GPU training, `CUDA_VISIBLE_DEVICES` needs to be set, and DALI needs to occupy GPU memory, so it needs to reserve GPU memory for Dali. To train with DALI, just set the fields in the training config `use_dali = True`, or start the training by the following command: + + +## 3. Using DALI + +Paddleclas supports training with DALI. Since DALI only supports GPU training, `CUDA_VISIBLE_DEVICES` needs to be set, and DALI needs to occupy GPU memory, so it needs to reserve GPU memory for Dali. To train with DALI, just set the fields in the training config `use_dali = True`, or start the training by the following command: ```shell # set the GPUs that can be seen export CUDA_VISIBLE_DEVICES="0" -# set the GPU memory used for neural network training, generally 0.8 or 0.7, and the remaining GPU memory is reserved for DALI -export FLAGS_fraction_of_gpu_memory_to_use=0.80 - -python tools/static/train.py -c configs/ResNet/ResNet50.yaml -o use_dali=True +python ppcls/train.py -c ppcls/configs/ImageNet/ResNet/ResNet50.yaml -o Global.use_dali=True ``` And you can train with muti-GPUs: ```shell # set the GPUs that can be seen -export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7" +export CUDA_VISIBLE_DEVICES="0,1,2,3" # set the GPU memory used for neural network training, generally 0.8 or 0.7, and the remaining GPU memory is reserved for DALI export FLAGS_fraction_of_gpu_memory_to_use=0.80 python -m paddle.distributed.launch \ - --gpus="0,1,2,3,4,5,6,7" \ - tools/static/train.py \ - -c ./configs/ResNet/ResNet50.yaml \ - -o use_dali=True + --gpus="0,1,2,3" \ + ppcls/train.py \ + -c ./ppcls/configs/ImageNet/ResNet/ResNet50.yaml \ + -o Global.use_dali=True ``` -## Train with FP16 + + +## 4. Train with FP16 On the basis of the above, using FP16 half-precision can further improve the training speed, you can refer to the following command. ```shell -export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 +export CUDA_VISIBLE_DEVICES=0,1,2,3 export FLAGS_fraction_of_gpu_memory_to_use=0.8 python -m paddle.distributed.launch \ - --gpus="0,1,2,3,4,5,6,7" \ - tools/static/train.py \ - -c configs/ResNet/ResNet50_fp16.yaml + --gpus="0,1,2,3" \ + ppcls/train.py \ + -c ./ppcls/configs/ImageNet/ResNet/ResNet50_fp16_dygraph.yaml ```