[Enhancement] Improve get_started documents and bump version to 0.7.0 (…

…open-mmlab#813) * simplify commands in get_started * add installation commands for Windows * fix typo * limit markdown and sphinx_markdown_tables version * adopt html <details open> tag * bump mmdeploy version * bump mmdeploy version * update get_started * update get_started * use python3.8 instead of python3.7 * remove duplicate section * resolve issue open-mmlab#856 * update according to review results * add reference to prebuilt_package_windows.md * fix error when build sdk demos
RunningLeon · Aug 4, 2022 · 83b11bc · 83b11bc
1 parent ef56036
commit 83b11bc
Show file tree

Hide file tree

Showing 18 changed files with 419 additions and 520 deletions.
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -5,7 +5,7 @@ endif ()
 message(STATUS "CMAKE_INSTALL_PREFIX: ${CMAKE_INSTALL_PREFIX}")
 
 cmake_minimum_required(VERSION 3.14)
-project(MMDeploy VERSION 0.6.0)
+project(MMDeploy VERSION 0.7.0)
 
 set(CMAKE_CXX_STANDARD 17)
 

diff --git a/docker/CPU/Dockerfile b/docker/CPU/Dockerfile
@@ -93,6 +93,7 @@ RUN git clone https://github.com/open-mmlab/mmdeploy.git &&\
 ENV LD_LIBRARY_PATH="/root/workspace/mmdeploy/build/lib:/opt/intel/openvino/deployment_tools/ngraph/lib:/opt/intel/openvino/deployment_tools/inference_engine/lib/intel64:${LD_LIBRARY_PATH}"
 RUN cd mmdeploy && rm -rf build/CM* && mkdir -p build && cd build && cmake .. \
     -DMMDEPLOY_BUILD_SDK=ON \
+    -DMMDEPLOY_BUILD_EXAMPLES=ON \
     -DCMAKE_CXX_COMPILER=g++-7 \
     -DONNXRUNTIME_DIR=${ONNXRUNTIME_DIR} \
     -Dncnn_DIR=/root/workspace/ncnn/build/install/lib/cmake/ncnn \
@@ -102,9 +103,5 @@ RUN cd mmdeploy && rm -rf build/CM* && mkdir -p build && cd build && cmake .. \
     -DMMDEPLOY_TARGET_BACKENDS="ort;ncnn;openvino" \
     -DMMDEPLOY_CODEBASES=all &&\
     cmake --build . -- -j$(nproc) && cmake --install . &&\
-    cd install/example  && mkdir -p build && cd build &&\
-    cmake .. -DMMDeploy_DIR=/root/workspace/mmdeploy/build/install/lib/cmake/MMDeploy \
-    -DInferenceEngine_DIR=/opt/intel/openvino/deployment_tools/inference_engine/share \
-    -Dncnn_DIR=/root/workspace/ncnn/build/install/lib/cmake/ncnn &&\
-    cmake --build . && export SPDLOG_LEVEL=warn &&\
+    export SPDLOG_LEVEL=warn &&\
     if [ -z ${VERSION} ] ; then echo "Built MMDeploy master for CPU devices successfully!" ; else echo "Built MMDeploy version v${VERSION} for CPU devices successfully!" ; fi
diff --git a/docker/GPU/Dockerfile b/docker/GPU/Dockerfile
@@ -79,6 +79,7 @@ RUN cd /root/workspace/mmdeploy &&\
     mkdir -p build && cd build &&\
     cmake .. \
         -DMMDEPLOY_BUILD_SDK=ON \
+        -DMMDEPLOY_BUILD_EXAMPLES=ON \
         -DCMAKE_CXX_COMPILER=g++ \
         -Dpplcv_DIR=/root/workspace/ppl.cv/cuda-build/install/lib/cmake/ppl \
         -DTENSORRT_DIR=${TENSORRT_DIR} \
@@ -88,9 +89,7 @@ RUN cd /root/workspace/mmdeploy &&\
         -DMMDEPLOY_TARGET_BACKENDS="ort;trt" \
         -DMMDEPLOY_CODEBASES=all &&\
     make -j$(nproc) && make install &&\
-    cd install/example  && mkdir -p build && cd build &&\
-    cmake -DMMDeploy_DIR=/root/workspace/mmdeploy/build/install/lib/cmake/MMDeploy .. &&\
-    make -j$(nproc) && export SPDLOG_LEVEL=warn &&\
+    export SPDLOG_LEVEL=warn &&\
     if [ -z ${VERSION} ] ; then echo "Built MMDeploy master for GPU devices successfully!" ; else echo "Built MMDeploy version v${VERSION} for GPU devices successfully!" ; fi
 
 ENV LD_LIBRARY_PATH="/root/workspace/mmdeploy/build/lib:${BACKUP_LD_LIBRARY_PATH}"
diff --git a/docs/en/01-how-to-build/android.md b/docs/en/01-how-to-build/android.md
@@ -7,8 +7,7 @@
       - [Install Dependencies for SDK](#install-dependencies-for-sdk)
     - [Build MMDeploy](#build-mmdeploy)
       - [Build Options Spec](#build-options-spec)
-      - [Build SDK](#build-sdk)
-      - [Build Demo](#build-demo)
+      - [Build SDK and Demos](#build-sdk-and-demos)
 
 ______________________________________________________________________
 
@@ -174,7 +173,7 @@ make -j$(nproc) install
 </tbody>
 </table>
 
-#### Build SDK
+#### Build SDK and Demos
 
 MMDeploy provides a recipe as shown below for building SDK with ncnn as inference engine for android.
 
@@ -186,6 +185,7 @@ MMDeploy provides a recipe as shown below for building SDK with ncnn as inferenc
   cmake .. \
       -DMMDEPLOY_BUILD_SDK=ON \
       -DMMDEPLOY_BUILD_SDK_JAVA_API=ON \
+      -DMMDEPLOY_BUILD_EXAMPLES=ON \
       -DOpenCV_DIR=${OPENCV_ANDROID_SDK_DIR}/sdk/native/jni/abi-${ANDROID_ABI} \
       -Dncnn_DIR=${NCNN_DIR}/build_${ANDROID_ABI}/install/lib/cmake/ncnn \
       -DMMDEPLOY_TARGET_BACKENDS=ncnn \
@@ -198,20 +198,3 @@ MMDeploy provides a recipe as shown below for building SDK with ncnn as inferenc
 
   make -j$(nproc) && make install
   ```
-
-#### Build Demo
-
-```Bash
-export ANDROID_ABI=arm64-v8a
-
-cd ${MMDEPLOY_DIR}/build_${ANDROID_ABI}/install/example
-mkdir -p build && cd build
-cmake .. \
-      -DOpenCV_DIR=${OPENCV_ANDROID_SDK_DIR}/sdk/native/jni/abi-${ANDROID_ABI} \
-      -Dncnn_DIR=${NCNN_DIR}/build_${ANDROID_ABI}/install/lib/cmake/ncnn \
-      -DMMDeploy_DIR=${MMDEPLOY_DIR}/build_${ANDROID_ABI}/install/lib/cmake/MMDeploy \
-      -DCMAKE_TOOLCHAIN_FILE=${NDK_PATH}/build/cmake/android.toolchain.cmake \
-      -DANDROID_ABI=${ANDROID_ABI} \
-      -DANDROID_PLATFORM=android-30
-make -j$(nproc)
-```
diff --git a/docs/en/01-how-to-build/jetsons.md b/docs/en/01-how-to-build/jetsons.md
@@ -251,13 +251,14 @@ It takes about 5 minutes to install model converter on a Jetson Nano. So, please
 
 ### Install C/C++ Inference SDK
 
-1. Build SDK Libraries
+Build SDK Libraries and its demo as below:
 
 ```shell
 mkdir -p build && cd build
 cmake .. \
     -DMMDEPLOY_BUILD_SDK=ON \
     -DMMDEPLOY_BUILD_SDK_PYTHON_API=ON \
+    -DMMDEPLOY_BUILD_EXAMPLES=ON \
     -DMMDEPLOY_TARGET_DEVICES="cuda;cpu" \
     -DMMDEPLOY_TARGET_BACKENDS="trt" \
     -DMMDEPLOY_CODEBASES=all \
@@ -269,15 +270,6 @@ make -j$(nproc) && make install
 It takes about 9 minutes to build SDK libraries on a Jetson Nano. So, please be patient until the installation is complete.
 ```
 
-2. Build SDK demos
-
-```shell
-cd ${MMDEPLOY_DIR}/build/install/example
-mkdir -p build && cd build
-cmake .. -DMMDeploy_DIR=${MMDEPLOY_DIR}/build/install/lib/cmake/MMDeploy
-make -j$(nproc)
-```
-
 ### Run a Demo
 
 #### Object Detection demo

diff --git a/docs/en/01-how-to-build/linux-x86_64.md b/docs/en/01-how-to-build/linux-x86_64.md
@@ -11,8 +11,7 @@
     - [Build Model Converter](#build-model-converter)
       - [Build Custom Ops](#build-custom-ops)
       - [Install Model Converter](#install-model-converter)
-    - [Build SDK](#build-sdk)
-    - [Build Demo](#build-demo)
+    - [Build SDK and Demo](#build-sdk-and-demo)
 
 ______________________________________________________________________
 
@@ -395,7 +394,7 @@ pip install -e .
   To use optional dependencies, install them manually with `pip install -r requirements/optional.txt` or specify desired extras when calling `pip` (e.g. `pip install -e .[optional]`).
   Valid keys for the extras field are: `all`, `tests`, `build`, `optional`.
 
-### Build SDK
+### Build SDK and Demo
 
 MMDeploy provides two recipes as shown below for building SDK with ONNXRuntime and TensorRT as inference engines respectively.
 You can also activate other engines after the model.
@@ -409,6 +408,7 @@ You can also activate other engines after the model.
       -DCMAKE_CXX_COMPILER=g++-7 \
       -DMMDEPLOY_BUILD_SDK=ON \
       -DMMDEPLOY_BUILD_SDK_PYTHON_API=ON \
+      -DMMDEPLOY_BUILD_EXAMPLES=ON \
       -DMMDEPLOY_TARGET_DEVICES=cpu \
       -DMMDEPLOY_TARGET_BACKENDS=ort \
       -DMMDEPLOY_CODEBASES=all \
@@ -426,6 +426,7 @@ You can also activate other engines after the model.
       -DCMAKE_CXX_COMPILER=g++-7 \
       -DMMDEPLOY_BUILD_SDK=ON \
       -DMMDEPLOY_BUILD_SDK_PYTHON_API=ON \
+      -DMMDEPLOY_BUILD_EXAMPLES=ON \
       -DMMDEPLOY_TARGET_DEVICES="cuda;cpu" \
       -DMMDEPLOY_TARGET_BACKENDS=trt \
       -DMMDEPLOY_CODEBASES=all \
@@ -435,12 +436,3 @@ You can also activate other engines after the model.
 
   make -j$(nproc) && make install
   ```
-
-### Build Demo
-
-```Bash
-cd ${MMDEPLOY_DIR}/build/install/example
-mkdir -p build && cd build
-cmake .. -DMMDeploy_DIR=${MMDEPLOY_DIR}/build/install/lib/cmake/MMDeploy
-make -j$(nproc)
-```
diff --git a/docs/en/01-how-to-build/windows.md b/docs/en/01-how-to-build/windows.md
@@ -12,14 +12,11 @@
       - [Build Model Converter](#build-model-converter)
         - [Build Custom Ops](#build-custom-ops)
         - [Install Model Converter](#install-model-converter)
-      - [Build SDK](#build-sdk)
-      - [Build Demo](#build-demo)
+      - [Build SDK and Demos](#build-sdk-and-demos)
     - [Note](#note)
 
 ______________________________________________________________________
 
-Currently, MMDeploy only provides build-from-source method for windows platform. Prebuilt package will be released in the future.
-
 ## Build From Source
 
 All the commands listed in the following chapters are verified on **Windows 10**.
@@ -315,7 +312,7 @@ pip install -e .
   To use optional dependencies, install them manually with `pip install -r requirements/optional.txt` or specify desired extras when calling `pip` (e.g. `pip install -e .[optional]`).
   Valid keys for the extras field are: `all`, `tests`, `build`, `optional`.
 
-#### Build SDK
+#### Build SDK and Demos
 
 MMDeploy provides two recipes as shown below for building SDK with ONNXRuntime and TensorRT as inference engines respectively.
 You can also activate other engines after the model.
@@ -328,6 +325,8 @@ You can also activate other engines after the model.
   cd build
   cmake .. -G "Visual Studio 16 2019" -A x64 -T v142 `
       -DMMDEPLOY_BUILD_SDK=ON `
+      -DMMDEPLOY_BUILD_EXAMPLES=ON `
+      -DMMDEPLOY_BUILD_SDK_PYTHON_API=ON `
       -DMMDEPLOY_TARGET_DEVICES="cpu" `
       -DMMDEPLOY_TARGET_BACKENDS="ort" `
       -DMMDEPLOY_CODEBASES="all" `
@@ -345,6 +344,8 @@ You can also activate other engines after the model.
   cd build
   cmake .. -G "Visual Studio 16 2019" -A x64 -T v142 `
     -DMMDEPLOY_BUILD_SDK=ON `
+    -DMMDEPLOY_BUILD_EXAMPLES=ON `
+    -DMMDEPLOY_BUILD_SDK_PYTHON_API=ON `
     -DMMDEPLOY_TARGET_DEVICES="cuda" `
     -DMMDEPLOY_TARGET_BACKENDS="trt" `
     -DMMDEPLOY_CODEBASES="all" `
@@ -356,20 +357,6 @@ You can also activate other engines after the model.
   cmake --install . --config Release
   ```
 
-#### Build Demo
-
-```PowerShell
-cd $env:MMDEPLOY_DIR\build\install\example
-mkdir build -ErrorAction SilentlyContinue
-cd build
-cmake .. -G "Visual Studio 16 2019" -A x64 -T v142 `
-  -DMMDeploy_DIR="$env:MMDEPLOY_DIR/build/install/lib/cmake/MMDeploy"
-
-cmake --build . --config Release -- /m
-
-$env:path = "$env:MMDEPLOY_DIR/build/install/bin;" + $env:path
-```
-
 ### Note
 
 1. Release / Debug libraries can not be mixed. If MMDeploy is built with Release mode, all its dependent thirdparty libraries have to be built in Release mode too and vice versa.
diff --git a/docs/en/02-how-to-run/prebuilt_package_windows.md b/docs/en/02-how-to-run/prebuilt_package_windows.md
@@ -21,7 +21,7 @@
 
 ______________________________________________________________________
 
-This tutorial takes `mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1.zip` and `mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0.zip` as examples to show how to use the prebuilt packages.
+This tutorial takes `mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1.zip` and `mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8.2.3.0.zip` as examples to show how to use the prebuilt packages.
 
 The directory structure of the prebuilt package is as follows, where the `dist` folder is about model converter, and the `sdk` folder is related to model inference.
 
@@ -80,9 +80,9 @@ In order to use `ONNX Runtime` backend, you should also do the following steps.
 5. Install `mmdeploy` (Model Converter) and `mmdeploy_python` (SDK Python API).
 
    ```bash
-   # download mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1.zip
-   pip install .\mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1\dist\mmdeploy-0.6.0-py38-none-win_amd64.whl
-   pip install .\mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1\sdk\python\mmdeploy_python-0.6.0-cp38-none-win_amd64.whl
+   # download mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1.zip
+   pip install .\mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1\dist\mmdeploy-0.7.0-py38-none-win_amd64.whl
+   pip install .\mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1\sdk\python\mmdeploy_python-0.7.0-cp38-none-win_amd64.whl
    ```
 
    :point_right: If you have installed it before, please uninstall it first.
@@ -107,9 +107,9 @@ In order to use `TensorRT` backend, you should also do the following steps.
 5. Install `mmdeploy` (Model Converter) and `mmdeploy_python` (SDK Python API).
 
    ```bash
-   # download mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0.zip
-   pip install .\mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\dist\mmdeploy-0.6.0-py38-none-win_amd64.whl
-   pip install .\mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\sdk\python\mmdeploy_python-0.6.0-cp38-none-win_amd64.whl
+   # download mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8.2.3.0.zip
+   pip install .\mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\dist\mmdeploy-0.7.0-py38-none-win_amd64.whl
+   pip install .\mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\sdk\python\mmdeploy_python-0.7.0-cp38-none-win_amd64.whl
    ```
 
    :point_right: If you have installed it before, please uninstall it first.
@@ -138,7 +138,7 @@ After preparation work, the structure of the current working directory should be
 
 ```
 ..
-|-- mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1
+|-- mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1
 |-- mmclassification
 |-- mmdeploy
 `-- resnet18_8xb32_in1k_20210831-fbbb1da6.pth
@@ -186,7 +186,7 @@ After installation of mmdeploy-tensorrt prebuilt package, the structure of the c
 
 ```
 ..
-|-- mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0
+|-- mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8.2.3.0
 |-- mmclassification
 |-- mmdeploy
 `-- resnet18_8xb32_in1k_20210831-fbbb1da6.pth
@@ -249,8 +249,8 @@ The structure of current working directory：
 
 ```
 .
-|-- mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0
-|-- mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1
+|-- mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8.2.3.0
+|-- mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1
 |-- mmclassification
 |-- mmdeploy
 |-- resnet18_8xb32_in1k_20210831-fbbb1da6.pth
@@ -294,13 +294,13 @@ The following describes how to use the SDK's Python API for inference
 #### ONNXRuntime
 
 ```bash
-python .\mmdeploy\demo\python\image_classification.py .\work_dir\onnx\resnet\ .\mmclassification\demo\demo.JPEG
+python .\mmdeploy\demo\python\image_classification.py cpu .\work_dir\onnx\resnet\ .\mmclassification\demo\demo.JPEG
 ```
 
 #### TensorRT
 
 ```
- python .\mmdeploy\demo\python\image_classification.py .\work_dir\trt\resnet\ .\mmclassification\demo\demo.JPEG --device-name cuda
+ python .\mmdeploy\demo\python\image_classification.py cuda .\work_dir\trt\resnet\ .\mmclassification\demo\demo.JPEG
 ```
 
 ### C SDK
@@ -311,15 +311,15 @@ The following describes how to use the SDK's C API for inference
 
 1. Build examples
 
-   Under `mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1\sdk\example` directory
+   Under `mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1\sdk\example` directory
 
    ```
    // Path should be modified according to the actual location
    mkdir build
    cd build
    cmake .. -A x64 -T v142 `
      -DOpenCV_DIR=C:\Deps\opencv\build\x64\vc15\lib `
-     -DMMDeploy_DIR=C:\workspace\mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1\sdk\lib\cmake\MMDeploy `
+     -DMMDeploy_DIR=C:\workspace\mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1\sdk\lib\cmake\MMDeploy `
      -DONNXRUNTIME_DIR=C:\Deps\onnxruntime\onnxruntime-win-gpu-x64-1.8.1
 
    cmake --build . --config Release
@@ -329,15 +329,15 @@ The following describes how to use the SDK's C API for inference
 
    :point_right: The purpose is to make the exe find the relevant dll
 
-   If choose to add environment variables, add the runtime libraries path of `mmdeploy` (`mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1\sdk\bin`) to the `PATH`.
+   If choose to add environment variables, add the runtime libraries path of `mmdeploy` (`mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1\sdk\bin`) to the `PATH`.
 
    If choose to copy the dynamic libraries, copy the dll in the bin directory to the same level directory of the just compiled exe (build/Release).
 
 3. Inference：
 
    It is recommended to use `CMD` here.
 
-   Under `mmdeploy-0.6.0-windows-amd64-onnxruntime1.8.1\\sdk\\example\\build\\Release` directory：
+   Under `mmdeploy-0.7.0-windows-amd64-onnxruntime1.8.1\\sdk\\example\\build\\Release` directory：
 
    ```
    .\image_classification.exe cpu C:\workspace\work_dir\onnx\resnet\ C:\workspace\mmclassification\demo\demo.JPEG
@@ -347,15 +347,15 @@ The following describes how to use the SDK's C API for inference
 
 1. Build examples
 
-   Under `mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\\sdk\\example` directory
+   Under `mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\\sdk\\example` directory
 
    ```
    // Path should be modified according to the actual location
    mkdir build
    cd build
    cmake .. -A x64 -T v142 `
      -DOpenCV_DIR=C:\Deps\opencv\build\x64\vc15\lib `
-     -DMMDeploy_DIR=C:\workspace\mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8 2.3.0\sdk\lib\cmake\MMDeploy `
+     -DMMDeploy_DIR=C:\workspace\mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8 2.3.0\sdk\lib\cmake\MMDeploy `
      -DTENSORRT_DIR=C:\Deps\tensorrt\TensorRT-8.2.3.0 `
      -DCUDNN_DIR=C:\Deps\cudnn\8.2.1
    cmake --build . --config Release
@@ -365,15 +365,15 @@ The following describes how to use the SDK's C API for inference
 
    :point_right: The purpose is to make the exe find the relevant dll
 
-   If choose to add environment variables, add the runtime libraries path of `mmdeploy` (`mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\sdk\bin`) to the `PATH`.
+   If choose to add environment variables, add the runtime libraries path of `mmdeploy` (`mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\sdk\bin`) to the `PATH`.
 
    If choose to copy the dynamic libraries, copy the dll in the bin directory to the same level directory of the just compiled exe (build/Release).
 
 3. Inference
 
    It is recommended to use `CMD` here.
 
-   Under `mmdeploy-0.6.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\\sdk\\example\\build\\Release` directory
+   Under `mmdeploy-0.7.0-windows-amd64-cuda11.1-tensorrt8.2.3.0\\sdk\\example\\build\\Release` directory
 
    ```
    .\image_classification.exe cuda C:\workspace\work_dir\trt\resnet C:\workspace\mmclassification\demo\demo.JPEG