Currently `torch.onnx.export(.., operator_export_type=OperatorExportTypes.ONNX_ATEN_FALLBACK)` only issues ATen ops through explicit requests (e.g. `g.at()`) calls inside each op symbolic function. This is done based on specific conditions such as `operator_export_type==OperatorExportTypes.ONNX_ATEN_FALLBACK)` or `is_caffe2_aten_fallback()` This PR extends the ATen fallback mechanism for scenarios when the symbolic function raises `RuntimeError` during export. The idea is that partial implementation of existing ONNX ops can fallback to ATen as a last resort. That is valuable because each operator can have many input combinations and not all are always implemented. A minor fix was done to make sure the `overload_name` attribute is added to explicit ATen op fallback requests when a symbolic is not registered to a particular op. ps: The behavior for builds with BUILD_CAFFE2=1 is not changed to ensure BC. Pull Request resolved: https://github.com/pytorch/pytorch/pull/74759 Approved by: https://github.com/garymm, https://github.com/msaroufim |
||
|---|---|---|
| .. | ||
| appveyor | ||
| fbcode-dev-setup | ||
| jit | ||
| model_zoo | ||
| onnx | ||
| release | ||
| release_notes | ||
| add_apache_header.sh | ||
| apache_header.txt | ||
| apache_python.txt | ||
| build_android.sh | ||
| build_host_protoc.sh | ||
| build_ios.sh | ||
| build_local.sh | ||
| build_mobile.sh | ||
| build_pytorch_android.sh | ||
| build_raspbian.sh | ||
| build_tegra_x1.sh | ||
| build_tizen.sh | ||
| build_windows.bat | ||
| diagnose_protobuf.py | ||
| get_python_cmake_flags.py | ||
| proto.ps1 | ||
| read_conda_versions.sh | ||
| README.md | ||
| remove_apache_header.sh | ||
| temp.sh | ||
| xcode_build.rb | ||
This directory contains the useful tools.
build_android.sh
This script is to build PyTorch/Caffe2 library for Android. Take the following steps to start the build:
- set ANDROID_NDK to the location of ndk
export ANDROID_NDK=YOUR_NDK_PATH
- run build_android.sh
#in your PyTorch root directory
bash scripts/build_android.sh
If succeeded, the libraries and headers would be generated to build_android/install directory. You can then copy these files from build_android/install to your Android project for further usage.
You can also override the cmake flags via command line, e.g., following command will also compile the executable binary files:
bash scripts/build_android.sh -DBUILD_BINARY=ON
build_ios.sh
This script is to build PyTorch/Caffe2 library for iOS, and can only be performed on macOS. Take the following steps to start the build:
- Install Xcode from App Store, and configure "Command Line Tools" properly on Xcode.
- Install the dependencies:
brew install cmake automake libtool
- run build_ios.sh
#in your PyTorch root directory
bash scripts/build_ios.sh
If succeeded, the libraries and headers would be generated to build_ios/install directory. You can then copy these files to your Xcode project for further usage.