We can run the Docker image we just created to build the inference library of PaddlePaddle for Android using the command below:
We can run the Docker image we just created to build the inference library of PaddlePaddle for Android using the command below:
@ -47,7 +56,7 @@ The Docker image accepts two arguments `ANDROID_ABI` and `ANDROID_API`:
</tr>
</tr>
<trclass="row-odd">
<trclass="row-odd">
<td>ANDROID_API</td>
<td>ANDROID_API</td>
<td>>= 21</td>
<td>>= 16</td>
<td>21</td>
<td>21</td>
</tr>
</tr>
</tbody>
</tbody>
@ -93,15 +102,13 @@ Android NDK includes everything we need to build the [*standalone toolchain*](ht
The generated standalone toolchain will be in `your/path/to/arm64_standalone_toolchain`.
The generated standalone toolchain will be in `your/path/to/arm64_standalone_toolchain`.
**Please be aware that the minimum level of Android API required by PaddlePaddle is 21.**
### Cross-Compiling Arguments
### Cross-Compiling Arguments
CMake supports [choosing the toolchain](https://cmake.org/cmake/help/v3.0/manual/cmake-toolchains.7.html#cross-compiling). PaddlePaddle provides [`android.cmake`](https://github.com/PaddlePaddle/Paddle/blob/develop/cmake/cross_compiling/android.cmake), which configures the Android cross-compiling toolchain for CMake. `android.cmake` is not required for CMake >= 3.7, which support Android cross-compiling. PaddlePaddle detects the CMake version, for those newer than 3.7, it uses [the official version](https://cmake.org/cmake/help/v3.7/manual/cmake-toolchains.7.html#cross-compiling).
CMake supports [choosing the toolchain](https://cmake.org/cmake/help/v3.0/manual/cmake-toolchains.7.html#cross-compiling). PaddlePaddle provides [`android.cmake`](https://github.com/PaddlePaddle/Paddle/blob/develop/cmake/cross_compiling/android.cmake), which configures the Android cross-compiling toolchain for CMake. `android.cmake` is not required for CMake >= 3.7, which support Android cross-compiling. PaddlePaddle detects the CMake version, for those newer than 3.7, it uses [the official version](https://cmake.org/cmake/help/v3.7/manual/cmake-toolchains.7.html#cross-compiling).
Some other CMake arguments you need to know:
Some other CMake arguments you need to know:
- `CMAKE_SYSTEM_NAME` must be `Android`. This tells PaddlePaddle's CMake system to cross-compile third-party dependencies. This also changes some other CMake arguments like `WITH_GPU=OFF`, `WITH_AVX=OFF`, `WITH_PYTHON=OFF`, and `WITH_RDMA=OFF`.
- `CMAKE_SYSTEM_NAME` must be `Android`. This tells PaddlePaddle's CMake system to cross-compile third-party dependencies. This also changes some other CMake arguments like `WITH_GPU=OFF`, `WITH_AVX=OFF`, `WITH_PYTHON=OFF`, `WITH_RDMA=OFF`, `WITH_MKL=OFF` and `WITH_GOLANG=OFF`.
- `WITH_C_API` must be `ON`, to build the C-based inference library for Android.
- `WITH_C_API` must be `ON`, to build the C-based inference library for Android.
- `WITH_SWIG_PY` must be `OFF` because the Android platform doesn't support SWIG-based API.
- `WITH_SWIG_PY` must be `OFF` because the Android platform doesn't support SWIG-based API.
@ -123,7 +130,7 @@ Some Android-specific arguments:
Other useful arguments:
Other useful arguments:
- `USE_EIGEN_FOR_BLAS`: indicates if using Eigen. Could be `ON` or `OFF`, defaults to `OFF`.
- `USE_EIGEN_FOR_BLAS`: indicates if using Eigen. Could be `ON` or `OFF`, defaults to `OFF`.
- `HOST_C/CXX_COMPILER`: specifies the host compiler, which is used to build the host-specific protoc and target-specific OpenBLAS. It defaults to the value of the environment variable `CC`, or `cc`.
- `HOST_C/CXX_COMPILER`: specifies the host compiler, which is used to build the host-specific protoc and target-specific OpenBLAS. It defaults to the value of the environment variable `CC/C++`, or `cc/c++`.
Some frequent configurations for your reference:
Some frequent configurations for your reference:
@ -158,6 +165,7 @@ There are some other arguments you might want to configure.
- `CMAKE_BUILD_TYPE-Release` optimizes the runtime performance.
- `CMAKE_BUILD_TYPE-Release` optimizes the runtime performance.
Our own tip for performance optimization to use clang and Eigen or OpenBLAS:
Our own tip for performance optimization to use clang and Eigen or OpenBLAS:
- `CMAKE_BUILD_TYPE=Release`
- `CMAKE_BUILD_TYPE=Release`
- `ANDROID_TOOLCHAIN=clang`
- `ANDROID_TOOLCHAIN=clang`
- `USE_EIGEN_BLAS=ON` for `armeabi-v7a`, or `USE_EIGEN_FOR_BLAS=OFF` for `arm64-v8a`.
- `USE_EIGEN_BLAS=ON` for `armeabi-v7a`, or `USE_EIGEN_FOR_BLAS=OFF` for `arm64-v8a`.
This tutorial will walk you through cross compiling the PaddlePaddle library for iOS from the source in MacOS.
This tutorial will walk you through cross compiling the PaddlePaddle library for iOS from the source in MacOS.
@ -98,7 +98,7 @@ You can set other compiling parameters for your own need. I.E. if you are trying
- set `CMAKE_BUILD_TYPE` with `Release`
- set `CMAKE_BUILD_TYPE` with `Release`
- set `IOS_USE_VECLIB_FOR_BLAS` with `ON`
- set `IOS_USE_VECLIB_FOR_BLAS` with `ON`
## Compile and install
## Build and install
After CMake, run following commands, PaddlePaddle will download the compile 3rd party dependencies, compile and install PaddlePaddle inference library.
After CMake, run following commands, PaddlePaddle will download the compile 3rd party dependencies, compile and install PaddlePaddle inference library.
@ -109,7 +109,7 @@ $ make install
Please Note: if you compiled PaddlePaddle in the source directory for other platforms, do remove `third_party` and `build` directory within the source with `rm -rf` to ensure that all the 3rd party libraries dependencies and PaddlePaddle is newly compiled with current CMake configuration.
Please Note: if you compiled PaddlePaddle in the source directory for other platforms, do remove `third_party` and `build` directory within the source with `rm -rf` to ensure that all the 3rd party libraries dependencies and PaddlePaddle is newly compiled with current CMake configuration.
`your/path/to/install` directory will have following directories after `compile` and `install`:
`your/path/to/install` directory will have following directories after `make install`:
Tao Luo
7 years ago
committed by
GitHub