add part code

docs/zh_cn/experimental/onnx_optimizer.md

+# ONNX export Optimizer
+
+This is a tool to optimize ONNX model when exporting from PyTorch.
+
+## Installation
+
+Build MMDeploy with `torchscript` support:
+
+```shell
+export Torch_DIR=$(python -c "import torch;print(torch.utils.cmake_prefix_path + '/Torch')")
+
+cmake \
+    -DTorch_DIR=${Torch_DIR} \
+    -DMMDEPLOY_TARGET_BACKENDS="${your_backend};torchscript" \
+    .. # You can also add other build flags if you need
+
+cmake --build . -- -j$(nproc) && cmake --install .
+```
+
+## Usage
+
+```python
+# import model_to_graph_custom_optimizer so we can hijack onnx.export
+from mmdeploy.apis.onnx.optimizer import model_to_graph__custom_optimizer # noqa
+from mmdeploy.core import RewriterContext
+from mmdeploy.apis.onnx.passes import optimize_onnx
+
+# load you model here
+model = create_model()
+
+# export with ONNX Optimizer
+x = create_dummy_input()
+with RewriterContext({}, onnx_custom_passes=optimize_onnx):
+    torch.onnx.export(model, x, output_path)
+```
+
+The model would be optimized after export.
+
+You can also define your own optimizer:
+
+```python
+# create the optimize callback
+def _optimize_onnx(graph, params_dict, torch_out):
+    from mmdeploy.backend.torchscript import ts_optimizer
+    ts_optimizer.onnx._jit_pass_onnx_peephole(graph)
+    return graph, params_dict, torch_out
+
+with RewriterContext({}, onnx_custom_passes=_optimize_onnx):
+    # export your model
+```

docs/zh_cn/faq.md

+# FAQ
+
+### TensorRT
+
+- "WARNING: Half2 support requested on hardware without native FP16 support, performance will be negatively affected."
+
+  Fp16 mode requires a device with full-rate fp16 support.
+
+- "error: parameter check failed at: engine.cpp::setBindingDimensions::1046, condition: profileMinDims.d[i] \<= dimensions.d[i]"
+
+  When building an `ICudaEngine` from an `INetworkDefinition` that has dynamically resizable inputs, users need to specify at least one optimization profile. Which can be set in deploy config:
+
+  ```python
+  backend_config = dict(
+    common_config=dict(max_workspace_size=1 << 30),
+    model_inputs=[
+        dict(
+            input_shapes=dict(
+                input=dict(
+                    min_shape=[1, 3, 320, 320],
+                    opt_shape=[1, 3, 800, 1344],
+                    max_shape=[1, 3, 1344, 1344])))
+    ])
+  ```
+
+  The input tensor shape should be limited between `min_shape` and `max_shape`.
+
+- "error: [TensorRT] INTERNAL ERROR: Assertion failed: cublasStatus == CUBLAS_STATUS_SUCCESS"
+
+  TRT 7.2.1 switches to use cuBLASLt (previously it was cuBLAS). cuBLASLt is the defaulted choice for SM version >= 7.0. You may need CUDA-10.2 Patch 1 (Released Aug 26, 2020) to resolve some cuBLASLt issues. Another option is to use the new TacticSource API and disable cuBLASLt tactics if you dont want to upgrade.
+
+### Libtorch
+
+- Error: `libtorch/share/cmake/Caffe2/Caffe2Config.cmake:96 (message):Your installed Caffe2 version uses cuDNN but I cannot find the cuDNN libraries.  Please set the proper cuDNN prefixes and / or install cuDNN.`
+
+  May `export CUDNN_ROOT=/root/path/to/cudnn` to resolve the build error.
+
+### Windows
+
+- Error: similar like this `OSError: [WinError 1455] The paging file is too small for this operation to complete. Error loading "C:\Users\cx\miniconda3\lib\site-packages\torch\lib\cudnn_cnn_infer64_8.dll" or one of its dependencies`
+
+  Solution: according to this [post](https://stackoverflow.com/questions/64837376/how-to-efficiently-run-multiple-pytorch-processes-models-at-once-traceback), the issue may be caused by NVidia and will fix in *CUDA release 11.7*. For now one could use the [fixNvPe.py](https://gist.github.com/cobryan05/7d1fe28dd370e110a372c4d268dcb2e5) script to modify the nvidia dlls in the pytorch lib dir.
+
+  `python fixNvPe.py --input=C:\Users\user\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\lib\*.dll`
+
+  You can find your pytorch installation path with:
+
+  ```python
+  import torch
+  print(torch.__file__)
+  ```
+
+- 编译时enable_language(CUDA) 报错
+
+  ```
+  -- Selecting Windows SDK version 10.0.19041.0 to target Windows 10.0.19044.
+  -- Found CUDA: C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v11.1 (found version "11.1")
+  CMake Error at C:/Software/cmake/cmake-3.23.1-windows-x86_64/share/cmake-3.23/Modules/CMakeDetermineCompilerId.cmake:491 (message):
+    No CUDA toolset found.
+  Call Stack (most recent call first):
+    C:/Software/cmake/cmake-3.23.1-windows-x86_64/share/cmake-3.23/Modules/CMakeDetermineCompilerId.cmake:6 (CMAKE_DETERMINE_COMPILER_ID_BUILD)
+    C:/Software/cmake/cmake-3.23.1-windows-x86_64/share/cmake-3.23/Modules/CMakeDetermineCompilerId.cmake:59 (__determine_compiler_id_test)
+    C:/Software/cmake/cmake-3.23.1-windows-x86_64/share/cmake-3.23/Modules/CMakeDetermineCUDACompiler.cmake:339 (CMAKE_DETERMINE_COMPILER_ID)
+    C:/workspace/mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0/sdk/lib/cmake/MMDeploy/MMDeployConfig.cmake:27 (enable_language)
+    CMakeLists.txt:5 (find_package)
+  ```
+
+  **原因：** CUDA Toolkit 11.1安装在Visual Studio之前，造成VS的插件没有安装。或者VS的版本过新，使得CUDA Toolkit的安装的时候跳过了VS插件的安装
+
+  **解决方法：** 可以通过手工拷贝插件的方式来解决这个问题。比如将`C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.1\extras\visual_studio_integration\MSBuildExtensions`中的四个文件拷贝到`C:\Software\Microsoft Visual Studio\2022\Community\Msbuild\Microsoft\VC\v170\BuildCustomizations` 目录下。具体路径根据实际情况进行更改。
+
+### ONNX Runtime
+
+- Windows系统下，转模型可视化时以及SDK推理时遇到
+  ```
+  onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Failed to load library, error code: 193
+  ```
+  **原因：** 在较新的windows系统中，系统路径下下有两个`onnxruntime.dll`，且会优先加载，造成冲突。
+  ```
+  C:\Windows\SysWOW64\onnxruntime.dll
+  C:\Windows\System32\onnxruntime.dll
+  ```
+  **解决方法：** 以下两个方案任选其一
+  1. 将下载的onnxruntime中的lib目录下的dll拷贝到mmdeploy_onnxruntime_ops.dll的同级目录（推荐使用Everything 进行查找）
+  2. 将系统路径下的这两个dll改名，使其加载不到，可能涉及到修改文件权限的操作
+
+### Pip
+
+- pip installed package but could not `import` them.
+
+  Make sure your are using conda pip.
+
+  ```bash
+  $ which pip
+  # /path/to/.local/bin/pip
+  /path/to/miniconda3/lib/python3.9/site-packages/pip
+  ```

docs/zh_cn/get_started.md

+# 操作概述
+
+MMDeploy 提供了一系列工具，帮助您更轻松的将 OpenMMLab 下的算法部署到各种设备与平台上。
+
+您可以使用我们设计的流程一“部”到位，也可以定制您自己的转换流程。
+
+## 流程简介
+
+MMDeploy 定义的模型部署流程，如下图所示：
+![deploy-pipeline](https://user-images.githubusercontent.com/4560679/172306700-31b4c922-2f04-42ed-a1d6-c360f2f3048c.png)
+
+### 模型转换（Model Converter）
+
+模型转换的主要功能是把输入的模型格式，转换为目标设备的推理引擎所要求的模型格式。
+
+目前，MMDeploy 可以把 PyTorch 模型转换为 ONNX、TorchScript 等和设备无关的 IR 模型。也可以将 ONNX 模型转换为推理后端模型。两者相结合，可实现端到端的模型转换，也就是从训练端到生产端的一键式部署。
+
+### MMDeploy 模型（MMDeploy Model）
+
+也称 SDK Model。它是模型转换结果的集合。不仅包括后端模型，还包括模型的元信息。这些信息将用于推理 SDK 中。
+
+### 推理 SDK（Inference SDK）
+
+封装了模型的前处理、网络推理和后处理过程。对外提供多语言的模型推理接口。
+
+## 准备工作
+
+对于端到端的模型转换和推理，MMDeploy 依赖 Python 3.6+ 以及 PyTorch 1.8+。
+
+**第一步**：从[官网](https://docs.conda.io/en/latest/miniconda.html)下载并安装 Miniconda
+
+**第二步**：创建并激活 conda 环境
+
+```shell
+conda create --name mmdeploy python=3.8 -y
+conda activate mmdeploy
+```
+
+**第三步**: 参考[官方文档](https://pytorch.org/get-started/locally/)并安装 PyTorch
+
+在 GPU 环境下：
+
+```shell
+conda install pytorch=={pytorch_version} torchvision=={torchvision_version} cudatoolkit={cudatoolkit_version} -c pytorch -c conda-forge
+```
+
+在 CPU 环境下：
+
+```shell
+conda install pytorch=={pytorch_version} torchvision=={torchvision_version} cpuonly -c pytorch
+```
+
+```{note}
+在 GPU 环境下，请务必保证 {cudatoolkit_version} 和主机的 CUDA Toolkit 版本一致，避免在使用 TensorRT 时，可能引起的版本冲突问题。
+```
+
+## 安装 MMDeploy
+
+**第一步**：通过 [MIM](https://github.com/open-mmlab/mim) 安装 [MMCV](https://github.com/open-mmlab/mmcv)
+
+```shell
+pip install -U openmim
+mim install "mmcv>=2.0.0rc2"
+```
+
+**第二步**: 安装 MMDeploy 和 推理引擎
+
+我们推荐用户使用预编译包安装和体验 MMDeploy 功能。目前提供模型转换(trt/ort)以及 SDK 推理的 pypi 预编译包，SDK 的 c/cpp 库可从[这里](https://github.com/open-mmlab/mmdeploy/releases) 选择最新版本下载并安装。
+
+目前，MMDeploy 的预编译包支持的平台和设备矩阵如下：
+
+<table>
+<thead>
+  <tr>
+    <th>OS-Arch</th>
+    <th>Device</th>
+    <th>ONNX Runtime</th>
+    <th>TensorRT</th>
+  </tr>
+</thead>
+<tbody>
+  <tr>
+    <td rowspan="2">Linux-x86_64</td>
+    <td>CPU</td>
+    <td>Y</td>
+    <td>N/A</td>
+  </tr>
+  <tr>
+    <td>CUDA</td>
+    <td>Y</td>
+    <td>Y</td>
+  </tr>
+  <tr>
+    <td rowspan="2">Windows-x86_64</td>
+    <td>CPU</td>
+    <td>Y</td>
+    <td>N/A</td>
+  </tr>
+  <tr>
+    <td>CUDA</td>
+    <td>Y</td>
+    <td>Y</td>
+  </tr>
+</tbody>
+</table>
+
+**注：对于不在上述表格中的软硬件平台，请参考[源码安装文档](01-how-to-build/build_from_source.md)，正确安装和配置 MMDeploy。**
+
+以最新的预编译包为例，你可以参考以下命令安装：
+
+<details open>
+<summary><b>Linux-x86_64</b></summary>
+
+```shell
+# 1. 安装 MMDeploy 模型转换工具（含trt/ort自定义算子）
+pip install mmdeploy==1.3.1
+
+# 2. 安装 MMDeploy SDK推理工具
+# 根据是否需要GPU推理可任选其一进行下载安装
+# 2.1 支持 onnxruntime 推理
+pip install mmdeploy-runtime==1.3.1
+# 2.2 支持 onnxruntime-gpu tensorrt 推理
+pip install mmdeploy-runtime-gpu==1.3.1
+
+# 3. 安装推理引擎
+# 3.1 安装推理引擎 TensorRT
+# !!! 若要进行 TensorRT 模型的转换以及推理，从 NVIDIA 官网下载 TensorRT-8.2.3.0 CUDA 11.x 安装包并解压到当前目录。
+pip install TensorRT-8.2.3.0/python/tensorrt-8.2.3.0-cp38-none-linux_x86_64.whl
+pip install pycuda
+export TENSORRT_DIR=$(pwd)/TensorRT-8.2.3.0
+export LD_LIBRARY_PATH=${TENSORRT_DIR}/lib:$LD_LIBRARY_PATH
+# !!! 另外还需要从 NVIDIA 官网下载 cuDNN 8.2.1 CUDA 11.x 安装包并解压到当前目录
+export CUDNN_DIR=$(pwd)/cuda
+export LD_LIBRARY_PATH=$CUDNN_DIR/lib64:$LD_LIBRARY_PATH
+
+# 3.2 安装推理引擎 ONNX Runtime
+# 根据是否需要GPU推理可任选其一进行下载安装
+# 3.2.1 onnxruntime
+wget https://github.com/microsoft/onnxruntime/releases/download/v1.8.1/onnxruntime-linux-x64-1.8.1.tgz
+tar -zxvf onnxruntime-linux-x64-1.8.1.tgz
+export ONNXRUNTIME_DIR=$(pwd)/onnxruntime-linux-x64-1.8.1
+export LD_LIBRARY_PATH=$ONNXRUNTIME_DIR/lib:$LD_LIBRARY_PATH
+# 3.2.2 onnxruntime-gpu
+pip install onnxruntime-gpu==1.8.1
+wget https://github.com/microsoft/onnxruntime/releases/download/v1.8.1/onnxruntime-linux-x64-gpu-1.8.1.tgz
+tar -zxvf onnxruntime-linux-x64-gpu-1.8.1.tgz
+export ONNXRUNTIME_DIR=$(pwd)/onnxruntime-linux-x64-gpu-1.8.1
+export LD_LIBRARY_PATH=$ONNXRUNTIME_DIR/lib:$LD_LIBRARY_PATH
+```
+
+</details>
+
+<details open>
+<summary><b>Windows-x86_64</b></summary>
+</details>
+
+请阅读 [这里](02-how-to-run/prebuilt_package_windows.md)，了解 MMDeploy 预编译包在 Windows 平台下的使用方法。
+
+## 模型转换
+
+在准备工作就绪后，我们可以使用 MMDeploy 中的工具 `tools/deploy.py`，将 OpenMMLab 的 PyTorch 模型转换成推理后端支持的格式。
+对于`tools/deploy.py` 的使用细节，请参考 [如何转换模型](02-how-to-run/convert_model.md)。
+
+以 [MMDetection](https://github.com/open-mmlab/mmdetection) 中的 `Faster R-CNN` 为例，我们可以使用如下命令，将 PyTorch 模型转换为 TenorRT 模型，从而部署到 NVIDIA GPU 上.
+
+```shell
+# 克隆 mmdeploy 仓库。转换时，需要使用 mmdeploy 仓库中的配置文件，建立转换流水线, `--recursive` 不是必须的
+git clone -b main --recursive https://github.com/open-mmlab/mmdeploy.git
+
+# 安装 mmdetection。转换时，需要使用 mmdetection 仓库中的模型配置文件，构建 PyTorch nn module
+git clone -b 3.x https://github.com/open-mmlab/mmdetection.git
+cd mmdetection
+mim install -v -e .
+cd ..
+
+# 下载 Faster R-CNN 模型权重
+wget -P checkpoints https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth
+
+# 执行转换命令，实现端到端的转换
+python mmdeploy/tools/deploy.py \
+    mmdeploy/configs/mmdet/detection/detection_tensorrt_dynamic-320x320-1344x1344.py \
+    mmdetection/configs/faster_rcnn/faster-rcnn_r50_fpn_1x_coco.py \
+    checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth \
+    mmdetection/demo/demo.jpg \
+    --work-dir mmdeploy_model/faster-rcnn \
+    --device cuda \
+    --dump-info
+```
+
+转换结果被保存在 `--work-dir` 指向的文件夹中。**该文件夹中不仅包含推理后端模型，还包括推理元信息。这些内容的整体被定义为 SDK Model。推理 SDK 将用它进行模型推理。**
+
+```{tip}
+把上述转换命令中的detection_tensorrt_dynamic-320x320-1344x1344.py 换成 detection_onnxruntime_dynamic.py，并修改 --device 为 cpu，
+即可以转出 onnx 模型，并用 ONNXRuntime 进行推理
+```
+
+## 模型推理
+
+在转换完成后，你既可以使用 Model Converter 进行推理，也可以使用 Inference SDK。
+
+### 使用 Model Converter 的推理 API
+
+Model Converter 屏蔽了推理后端接口的差异，对其推理 API 进行了统一封装，接口名称为 `inference_model`。
+
+以上文中 Faster R-CNN 的 TensorRT 模型为例，你可以使用如下方式进行模型推理工作：
+
+```python
+from mmdeploy.apis import inference_model
+result = inference_model(
+  model_cfg='mmdetection/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py',
+  deploy_cfg='mmdeploy/configs/mmdet/detection/detection_tensorrt_dynamic-320x320-1344x1344.py',
+  backend_files=['mmdeploy_model/faster-rcnn/end2end.engine'],
+  img='mmdetection/demo/demo.jpg',
+  device='cuda:0')
+```
+
+```{note}
+接口中的 model_path 指的是推理引擎文件的路径，比如例子当中end2end.engine文件的路径。路径必须放在 list 中，因为有的推理引擎模型结构和权重是分开存储的。
+```
+
+### 使用推理 SDK
+
+你可以直接运行预编译包中的 demo 程序，输入 SDK Model 和图像，进行推理，并查看推理结果。
+
+```shell
+wget https://github.com/open-mmlab/mmdeploy/releases/download/v1.3.1/mmdeploy-1.3.1-linux-x86_64-cuda11.8.tar.gz
+tar xf mmdeploy-1.3.1-linux-x86_64-cuda11.8
+
+cd mmdeploy-1.3.1-linux-x86_64-cuda11.8
+# 运行 python demo
+python example/python/object_detection.py cuda ../mmdeploy_model/faster-rcnn ../mmdetection/demo/demo.jpg
+# 运行 C/C++ demo
+# 根据文件夹内的 README.md 进行编译
+./bin/object_detection cuda ../mmdeploy_model/faster-rcnn ../mmdetection/demo/demo.jpg
+```
+
+```{note}
+以上述命令中，输入模型是 SDK Model 的路径（也就是 Model Converter 中 --work-dir 参数），而不是推理引擎文件的路径。
+因为 SDK 不仅要获取推理引擎文件，还需要推理元信息（deploy.json, pipeline.json）。它们合在一起，构成 SDK Model，存储在 --work-dir 下
+```
+
+除了 demo 程序，预编译包还提供了 SDK 多语言接口。你可以根据自己的项目需求，选择合适的语言接口，
+把 MMDeploy SDK 集成到自己的项目中，进行二次开发。
+
+#### Python API
+
+对于检测功能，你也可以参考如下代码，集成 MMDeploy SDK Python API 到自己的项目中：
+
+```python
+from mmdeploy_runtime import Detector
+import cv2
+
+# 读取图片
+img = cv2.imread('mmdetection/demo/demo.jpg')
+
+# 创建检测器
+detector = Detector(model_path='mmdeploy_models/faster-rcnn', device_name='cuda', device_id=0)
+# 执行推理
+bboxes, labels, _ = detector(img)
+# 使用阈值过滤推理结果，并绘制到原图中
+indices = [i for i in range(len(bboxes))]
+for index, bbox, label_id in zip(indices, bboxes, labels):
+  [left, top, right, bottom], score = bbox[0:4].astype(int),  bbox[4]
+  if score < 0.3:
+      continue
+  cv2.rectangle(img, (left, top), (right, bottom), (0, 255, 0))
+
+cv2.imwrite('output_detection.png', img)
+```
+
+更多示例，请查阅[这里](https://github.com/open-mmlab/mmdeploy/tree/main/demo/python)。
+
+#### C++ API
+
+使用 C++ API 进行模型推理的流程符合下面的模式：
+![image](https://user-images.githubusercontent.com/4560679/182554486-2bf0ff80-9e82-4a0f-bccc-5e1860444302.png)
+
+以下是具体过程：
+
+```C++
+#include <cstdlib>
+#include <opencv2/opencv.hpp>
+#include "mmdeploy/detector.hpp"
+
+int main() {
+  const char* device_name = "cuda";
+  int device_id = 0;
+
+  // mmdeploy SDK model，以上文中转出的 faster r-cnn 模型为例
+  std::string model_path = "mmdeploy_model/faster-rcnn";
+  std::string image_path = "mmdetection/demo/demo.jpg";
+
+  // 1. 读取模型
+  mmdeploy::Model model(model_path);
+  // 2. 创建预测器
+  mmdeploy::Detector detector(model, mmdeploy::Device{device_name, device_id});
+  // 3. 读取图像
+  cv::Mat img = cv::imread(image_path);
+  // 4. 应用预测器推理
+  auto dets = detector.Apply(img);
+  // 5. 处理推理结果: 此处我们选择可视化推理结果
+  for (int i = 0; i < dets.size(); ++i) {
+    const auto& box = dets[i].bbox;
+    fprintf(stdout, "box %d, left=%.2f, top=%.2f, right=%.2f, bottom=%.2f, label=%d, score=%.4f\n",
+            i, box.left, box.top, box.right, box.bottom, dets[i].label_id, dets[i].score);
+    if (dets[i].score < 0.3) {
+      continue;
+    }
+    cv::rectangle(img, cv::Point{(int)box.left, (int)box.top},
+                  cv::Point{(int)box.right, (int)box.bottom}, cv::Scalar{0, 255, 0});
+  }
+  cv::imwrite("output_detection.png", img);
+  return 0;
+}
+```
+
+在您的项目CMakeLists中，增加：
+
+```Makefile
+find_package(MMDeploy REQUIRED)
+target_link_libraries(${name} PRIVATE mmdeploy ${OpenCV_LIBS})
+```
+
+编译时，使用 -DMMDeploy_DIR，传入MMDeloyConfig.cmake所在的路径。它在预编译包中的sdk/lib/cmake/MMDeloy下。
+更多示例，请查阅[此处](https://github.com/open-mmlab/mmdeploy/tree/main/demo/csrc/cpp)。
+
+对于 C API、C# API、Java API 的使用方法，请分别阅读代码[C demos](https://github.com/open-mmlab/mmdeploy/tree/main/demo/csrc/c)， [C# demos](https://github.com/open-mmlab/mmdeploy/tree/main/demo/csharp) 和 [Java demos](https://github.com/open-mmlab/mmdeploy/tree/main/demo/java)。
+我们将在后续版本中详细讲述它们的用法。
+
+#### 加速预处理（实验性功能）
+
+若要对预处理进行加速，请查阅[此处](./02-how-to-run/fuse_transform.md)
+
+## 模型精度评估
+
+为了测试部署模型的精度，推理效率，我们提供了 `tools/test.py` 来帮助完成相关工作。以上文中的部署模型为例：
+
+```bash
+python mmdeploy/tools/test.py \
+    mmdeploy/configs/detection/detection_tensorrt_dynamic-320x320-1344x1344.py \
+    mmdetection/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py \
+    --model mmdeploy_model/faster-rcnn/end2end.engine \
+    --metrics ${METRICS} \
+    --device cuda:0
+```
+
+```{note}
+关于 --model 选项，当使用 Model Converter 进行推理时，它代表转换后的推理后端模型的文件路径。而当使用 SDK 测试模型精度时，该选项表示 MMDeploy Model 的路径.
+```
+
+请阅读 [如何进行模型评估](02-how-to-run/profile_model.md) 了解关于 `tools/test.py` 的使用细节。

docs/zh_cn/index.rst

+欢迎来到 MMDeploy 的中文文档！
+====================================
+
+点击页面左下角切换中英文。
+
+.. toctree::
+   :maxdepth: 2
+   :caption: 快速上手
+
+   get_started.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 编译
+
+   01-how-to-build/build_from_source.md
+   01-how-to-build/build_from_docker.md
+   01-how-to-build/build_from_script.md
+   01-how-to-build/cmake_option.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 运行和测试
+
+   02-how-to-run/convert_model.md
+   02-how-to-run/write_config.md
+   02-how-to-run/profile_model.md
+   02-how-to-run/quantize_model.md
+   02-how-to-run/useful_tools.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: SDK 使用
+
+   sdk_usage/index.rst
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Benchmark
+
+   03-benchmark/supported_models.md
+   03-benchmark/benchmark.md
+   03-benchmark/benchmark_edge.md
+   03-benchmark/benchmark_tvm.md
+   03-benchmark/quantization.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 支持的算法框架
+
+   04-supported-codebases/mmpretrain.md
+   04-supported-codebases/mmdet.md
+   04-supported-codebases/mmdet3d.md
+   04-supported-codebases/mmagic.md
+   04-supported-codebases/mmocr.md
+   04-supported-codebases/mmpose.md
+   04-supported-codebases/mmrotate.md
+   04-supported-codebases/mmseg.md
+   04-supported-codebases/mmaction2.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 支持的推理后端
+
+   05-supported-backends/ncnn.md
+   05-supported-backends/onnxruntime.md
+   05-supported-backends/openvino.md
+   05-supported-backends/pplnn.md
+   05-supported-backends/rknn.md
+   05-supported-backends/snpe.md
+   05-supported-backends/tensorrt.md
+   05-supported-backends/torchscript.md
+   05-supported-backends/tvm.md
+   05-supported-backends/coreml.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 自定义算子
+
+   06-custom-ops/ncnn.md
+   06-custom-ops/onnxruntime.md
+   06-custom-ops/tensorrt.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 开发者指南
+
+   07-developer-guide/architecture.md
+   07-developer-guide/support_new_model.md
+   07-developer-guide/support_new_backend.md
+   07-developer-guide/add_backend_ops_unittest.md
+   07-developer-guide/test_rewritten_models.md
+   07-developer-guide/partition_model.md
+   07-developer-guide/regression_test.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 实验特性
+
+   experimental/onnx_optimizer.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 新人解说
+
+   tutorial/01_introduction_to_model_deployment.md
+   tutorial/02_challenges.md
+   tutorial/03_pytorch2onnx.md
+   tutorial/04_onnx_custom_op.md
+   tutorial/05_onnx_model_editing.md
+   tutorial/06_introduction_to_tensorrt.md
+   tutorial/07_write_a_plugin.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 附录
+
+   appendix/cross_build_snpe_service.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 常见问题
+
+   faq.md
+
+.. toctree::
+   :caption: 语言切换
+
+   switch_language.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: API 文档
+
+   api.rst
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`search`

docs/zh_cn/make.bat

+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.http://sphinx-doc.org/
+	exit /b 1
+)
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
+
+:end
+popd

docs/zh_cn/sdk_usage/c/classifier.rst

+====================
+classifier.h
+====================
+
+.. doxygenstruct:: mmdeploy_classification_t
+   :members:
+   :undoc-members:
+
+.. doxygentypedef:: mmdeploy_classifier_t
+
+
+.. doxygenfunction:: mmdeploy_classifier_create
+
+.. doxygenfunction:: mmdeploy_classifier_create_by_path
+
+.. doxygenfunction:: mmdeploy_classifier_apply
+
+.. doxygenfunction:: mmdeploy_classifier_release_result
+
+.. doxygenfunction:: mmdeploy_classifier_destroy
+
+.. doxygenfunction:: mmdeploy_classifier_create_v2
+
+.. doxygenfunction:: mmdeploy_classifier_create_input
+
+.. doxygenfunction:: mmdeploy_classifier_apply_v2
+
+.. doxygenfunction:: mmdeploy_classifier_apply_async
+
+.. doxygenfunction:: mmdeploy_classifier_get_result

docs/zh_cn/sdk_usage/c/common.rst

+====================
+common.h
+====================
+
+
+.. doxygenenum:: mmdeploy_pixel_format_t
+
+.. doxygenenum:: mmdeploy_data_type_t
+
+.. doxygenenum:: mmdeploy_status_t
+
+.. doxygentypedef:: mmdeploy_device_t
+
+.. doxygentypedef:: mmdeploy_profiler_t
+
+.. doxygenstruct:: mmdeploy_mat_t
+   :members:
+   :undoc-members:
+
+.. doxygenstruct:: mmdeploy_rect_t
+   :members:
+   :undoc-members:
+
+.. doxygenstruct:: mmdeploy_point_t
+   :members:
+   :undoc-members:
+
+.. doxygentypedef:: mmdeploy_value_t
+
+.. doxygentypedef:: mmdeploy_context_t
+
+.. doxygenfunction:: mmdeploy_value_copy
+
+.. doxygenfunction:: mmdeploy_value_destroy
+
+.. doxygenfunction:: mmdeploy_device_create
+
+.. doxygenfunction:: mmdeploy_device_destroy
+
+.. doxygenfunction:: mmdeploy_profiler_create
+
+.. doxygenfunction:: mmdeploy_profiler_destroy
+
+.. doxygenfunction:: mmdeploy_context_create
+
+.. doxygenfunction:: mmdeploy_context_create_by_device
+
+.. doxygenfunction:: mmdeploy_context_destroy
+
+.. doxygenfunction:: mmdeploy_context_add
+
+.. doxygenfunction:: mmdeploy_common_create_input

docs/zh_cn/sdk_usage/c/detector.rst

+====================
+detector.h
+====================
+
+.. doxygenstruct:: mmdeploy_instance_mask_t
+   :members:
+   :undoc-members:
+
+.. doxygenstruct:: mmdeploy_detection_t
+   :members:
+   :undoc-members:
+
+.. doxygentypedef:: mmdeploy_detector_t
+
+.. doxygenfunction:: mmdeploy_detector_create
+
+.. doxygenfunction:: mmdeploy_detector_create_by_path
+
+.. doxygenfunction:: mmdeploy_detector_apply
+
+.. doxygenfunction:: mmdeploy_detector_release_result
+
+.. doxygenfunction:: mmdeploy_detector_destroy
+
+.. doxygenfunction:: mmdeploy_detector_create_v2
+
+.. doxygenfunction:: mmdeploy_detector_create_input
+
+.. doxygenfunction:: mmdeploy_detector_apply_v2
+
+.. doxygenfunction:: mmdeploy_detector_apply_async
+
+.. doxygenfunction:: mmdeploy_detector_get_result

docs/zh_cn/sdk_usage/c/executor.rst

+====================
+executor.h
+====================
+
+.. doxygentypedef:: mmdeploy_then_fn_t
+
+.. doxygentypedef:: mmdeploy_then_fn_v2_t
+
+.. doxygentypedef:: mmdeploy_then_fn_v3_t
+
+.. doxygentypedef:: mmdeploy_sender_t
+
+.. doxygentypedef:: mmdeploy_scheduler_t
+
+.. doxygentypedef:: mmdeploy_let_value_fn_t
+
+.. doxygenfunction:: mmdeploy_executor_inline
+
+.. doxygenfunction:: mmdeploy_executor_system_pool
+
+.. doxygenfunction:: mmdeploy_executor_create_thread_pool
+
+.. doxygenfunction:: mmdeploy_executor_create_thread
+
+.. doxygenfunction:: mmdeploy_executor_dynamic_batch
+
+.. doxygenfunction:: mmdeploy_scheduler_destroy
+
+.. doxygenfunction:: mmdeploy_sender_copy
+
+.. doxygenfunction:: mmdeploy_sender_destroy
+
+.. doxygenfunction:: mmdeploy_executor_just
+
+.. doxygenfunction:: mmdeploy_executor_schedule
+
+.. doxygenfunction:: mmdeploy_executor_transfer_just
+
+.. doxygenfunction:: mmdeploy_executor_transfer
+
+.. doxygenfunction:: mmdeploy_executor_on
+
+.. doxygenfunction:: mmdeploy_executor_then
+
+.. doxygenfunction:: mmdeploy_executor_let_value
+
+.. doxygenfunction:: mmdeploy_executor_split
+
+.. doxygenfunction:: mmdeploy_executor_when_all
+
+.. doxygenfunction:: mmdeploy_executor_ensure_started
+
+.. doxygenfunction:: mmdeploy_executor_start_detached
+
+.. doxygenfunction:: mmdeploy_executor_sync_wait
+
+.. doxygenfunction:: mmdeploy_executor_sync_wait_v2
+
+.. doxygenfunction:: mmdeploy_executor_execute

docs/zh_cn/sdk_usage/c/model.rst

+====================
+model.h
+====================
+
+.. doxygentypedef:: mmdeploy_model_t
+
+.. doxygenfunction:: mmdeploy_model_create_by_path
+
+.. doxygenfunction:: mmdeploy_model_create
+
+.. doxygenfunction:: mmdeploy_model_destroy

docs/zh_cn/sdk_usage/c/pipeline.rst

+====================
+pipeline.h
+====================
+
+
+.. doxygentypedef:: mmdeploy_pipeline_t
+
+.. doxygenfunction:: mmdeploy_pipeline_create_v3
+
+.. doxygenfunction:: mmdeploy_pipeline_create_from_model
+
+.. doxygenfunction:: mmdeploy_pipeline_apply
+
+.. doxygenfunction:: mmdeploy_pipeline_apply_async
+
+.. doxygenfunction:: mmdeploy_pipeline_destroy

docs/zh_cn/sdk_usage/c/pose_detector.rst

+====================
+pose_detector.h
+====================
+
+.. doxygenstruct:: mmdeploy_pose_detection_t
+   :members:
+   :undoc-members:
+
+.. doxygentypedef:: mmdeploy_pose_detector_t
+
+.. doxygenfunction:: mmdeploy_pose_detector_create
+
+.. doxygenfunction:: mmdeploy_pose_detector_create_by_path
+
+.. doxygenfunction:: mmdeploy_pose_detector_apply
+
+.. doxygenfunction:: mmdeploy_pose_detector_apply_bbox
+
+.. doxygenfunction:: mmdeploy_pose_detector_release_result
+
+.. doxygenfunction:: mmdeploy_pose_detector_destroy
+
+.. doxygenfunction:: mmdeploy_pose_detector_create_v2
+
+.. doxygenfunction:: mmdeploy_pose_detector_create_input
+
+.. doxygenfunction:: mmdeploy_pose_detector_apply_v2
+
+.. doxygenfunction:: mmdeploy_pose_detector_apply_async
+
+.. doxygenfunction:: mmdeploy_pose_detector_get_result

docs/zh_cn/sdk_usage/c/pose_tracker.rst

+====================
+pose_tracker.h
+====================
+
+.. doxygentypedef:: mmdeploy_pose_tracker_t
+
+.. doxygentypedef:: mmdeploy_pose_tracker_state_t
+
+.. doxygenstruct:: mmdeploy_pose_tracker_param_t
+   :members:
+   :undoc-members:
+
+.. doxygenstruct:: mmdeploy_pose_tracker_target_t
+   :members:
+   :undoc-members:
+
+.. doxygenfunction:: mmdeploy_pose_tracker_default_params
+
+.. doxygenfunction:: mmdeploy_pose_tracker_create
+
+.. doxygenfunction:: mmdeploy_pose_tracker_destroy
+
+.. doxygenfunction:: mmdeploy_pose_tracker_create_state
+
+.. doxygenfunction:: mmdeploy_pose_tracker_destroy_state
+
+.. doxygenfunction:: mmdeploy_pose_tracker_apply
+
+.. doxygenfunction:: mmdeploy_pose_tracker_release_result

docs/zh_cn/sdk_usage/c/rotated_detector.rst

+====================
+rotated_detector.h
+====================
+
+.. doxygenstruct:: mmdeploy_rotated_detection_t
+   :members:
+   :undoc-members:
+
+.. doxygentypedef:: mmdeploy_rotated_detector_t
+
+.. doxygenfunction:: mmdeploy_rotated_detector_create
+
+.. doxygenfunction:: mmdeploy_rotated_detector_create_by_path
+
+.. doxygenfunction:: mmdeploy_rotated_detector_apply
+
+.. doxygenfunction:: mmdeploy_rotated_detector_release_result
+
+.. doxygenfunction:: mmdeploy_rotated_detector_destroy
+
+.. doxygenfunction:: mmdeploy_rotated_detector_create_v2
+
+.. doxygenfunction:: mmdeploy_rotated_detector_create_input
+
+.. doxygenfunction:: mmdeploy_rotated_detector_apply_v2
+
+.. doxygenfunction:: mmdeploy_rotated_detector_apply_async
+
+.. doxygenfunction:: mmdeploy_rotated_detector_get_result

docs/zh_cn/sdk_usage/c/segmentor.rst

+====================
+segmentor.h
+====================
+
+.. doxygenstruct:: mmdeploy_segmentation_t
+   :members:
+   :undoc-members:
+
+.. doxygentypedef:: mmdeploy_segmentor_t
+
+.. doxygenfunction:: mmdeploy_segmentor_create
+
+.. doxygenfunction:: mmdeploy_segmentor_create_by_path
+
+.. doxygenfunction:: mmdeploy_segmentor_apply
+
+.. doxygenfunction:: mmdeploy_segmentor_release_result
+
+.. doxygenfunction:: mmdeploy_segmentor_destroy
+
+.. doxygenfunction:: mmdeploy_segmentor_create_v2
+
+.. doxygenfunction:: mmdeploy_segmentor_create_input
+
+.. doxygenfunction:: mmdeploy_segmentor_apply_v2
+
+.. doxygenfunction:: mmdeploy_segmentor_apply_async
+
+.. doxygenfunction:: mmdeploy_segmentor_get_result

docs/zh_cn/sdk_usage/c/text_detector.rst

+====================
+text_detector.h
+====================
+
+.. doxygenstruct:: mmdeploy_text_detection_t
+   :members:
+   :undoc-members:
+
+.. doxygentypedef:: mmdeploy_text_detector_t
+
+.. doxygenfunction:: mmdeploy_text_detector_create
+
+.. doxygenfunction:: mmdeploy_text_detector_create_by_path
+
+.. doxygenfunction:: mmdeploy_text_detector_apply
+
+.. doxygenfunction:: mmdeploy_text_detector_release_result
+
+.. doxygenfunction:: mmdeploy_text_detector_destroy
+
+.. doxygenfunction:: mmdeploy_text_detector_create_v2
+
+.. doxygenfunction:: mmdeploy_text_detector_create_input
+
+.. doxygenfunction:: mmdeploy_text_detector_apply_v2
+
+.. doxygenfunction:: mmdeploy_text_detector_apply_async
+
+.. doxygenfunction:: mmdeploy_text_detector_get_result
+
+.. doxygentypedef:: mmdeploy_text_detector_continue_t
+
+.. doxygenfunction:: mmdeploy_text_detector_apply_async_v3
+
+.. doxygenfunction:: mmdeploy_text_detector_continue_async

docs/zh_cn/sdk_usage/c/text_recognizer.rst

+====================
+text_recognizer.h
+====================
+
+.. doxygenstruct:: mmdeploy_text_recognition_t
+   :members:
+   :undoc-members:
+
+.. doxygentypedef:: mmdeploy_text_recognizer_t
+
+.. doxygenfunction:: mmdeploy_text_recognizer_create
+
+.. doxygenfunction:: mmdeploy_text_recognizer_create_by_path
+
+.. doxygenfunction:: mmdeploy_text_recognizer_apply
+
+.. doxygenfunction:: mmdeploy_text_recognizer_apply_bbox
+
+.. doxygenfunction:: mmdeploy_text_recognizer_release_result
+
+.. doxygenfunction:: mmdeploy_text_recognizer_destroy
+
+.. doxygenfunction:: mmdeploy_text_recognizer_create_v2
+
+.. doxygenfunction:: mmdeploy_text_recognizer_create_input
+
+.. doxygenfunction:: mmdeploy_text_recognizer_apply_v2
+
+.. doxygenfunction:: mmdeploy_text_recognizer_apply_async
+
+.. doxygenfunction:: mmdeploy_text_recognizer_apply_async_v3
+
+.. doxygenfunction:: mmdeploy_text_recognizer_continue_async
+
+.. doxygenfunction:: mmdeploy_text_recognizer_get_result

docs/zh_cn/sdk_usage/c/video_recognizer.rst

+====================
+video_recognizer.h
+====================
+
+.. doxygenstruct:: mmdeploy_video_recognition_t
+   :members:
+   :undoc-members:
+
+.. doxygenstruct:: mmdeploy_video_sample_info_t
+   :members:
+   :undoc-members:
+
+.. doxygentypedef:: mmdeploy_video_recognizer_t
+
+.. doxygenfunction:: mmdeploy_video_recognizer_create
+
+.. doxygenfunction:: mmdeploy_video_recognizer_create_by_path
+
+.. doxygenfunction:: mmdeploy_video_recognizer_apply
+
+.. doxygenfunction:: mmdeploy_video_recognizer_release_result
+
+.. doxygenfunction:: mmdeploy_video_recognizer_destroy
+
+.. doxygenfunction:: mmdeploy_video_recognizer_create_v2
+
+.. doxygenfunction:: mmdeploy_video_recognizer_create_input
+
+.. doxygenfunction:: mmdeploy_video_recognizer_apply_v2
+
+.. doxygenfunction:: mmdeploy_video_recognizer_get_result

docs/zh_cn/sdk_usage/c_api.rst

+====================
+C API Reference
+====================
+
+
+.. toctree::
+   :maxdepth: 1
+
+   c/common
+   c/executor
+   c/model
+   c/pipeline
+   c/classifier
+   c/detector
+   c/pose_detector
+   c/pose_tracker
+   c/rotated_detector
+   c/segmentor
+   c/text_detector
+   c/text_recognizer
+   c/video_recognizer

docs/zh_cn/sdk_usage/index.rst

+========================
+SDK 使用说明
+========================
+
+安装 & 使用方法
+----------------
+.. toctree::
+   :maxdepth: 1
+
+   quick_start
+   profiler
+
+
+API Reference
+----------------
+.. toctree::
+   :maxdepth: 1
+
+   c_api