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)。
@@ -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)
<aname="1"></a>
## 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.
<aname="2"></a>
## 2. Export classification model
Change the working directory to PaddleClas:
...
...
@@ -43,11 +45,13 @@ python tools/export_model.py
```
<aname="3"></a>
## 3. Export mainbody detection model
About exporting mainbody detection model in details, please refer[mainbody detection](../image_recognition_pipeline/mainbody_detection_en.md).
<aname="4"></a>
## 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.
<aname="5"></a>
## 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.
[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)
<aname='1'></a>
## 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.
<aname='2'></a>
## 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:
<aname='3'></a>
## 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
