Register PRelu into quantization ops #20686
Conversation
|
@adrianlizarraga @xadupre Could you please help to review it? |
|
/azp run Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, ONNX Runtime Web CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline, Linux QNN CI Pipeline |
|
Azure Pipelines successfully started running 9 pipeline(s). |
|
/azp run Windows CPU CI Pipeline, Windows GPU CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows ARM64 QNN CI Pipeline, orttraining-linux-ci-pipeline, orttraining-linux-gpu-ci-pipeline, orttraining-ortmodule-distributed, Windows x64 QNN CI Pipeline, Linux MIGraphX CI Pipeline, Big Models |
|
Azure Pipelines successfully started running 10 pipeline(s). |
|
/azp run ONNX Runtime React Native CI Pipeline, orttraining-amd-gpu-ci-pipeline, Linux Android Emulator QNN CI Pipeline |
|
Azure Pipelines successfully started running 3 pipeline(s). |
There was a problem hiding this comment.
Hi @UsingtcNower, could you please add a unit test to verify functionality? The unit tests are located here: https://github.com/microsoft/onnxruntime/tree/main/onnxruntime/test/python/quantization
To run them locally:
- Build onnxruntime locally with the
--build_wheeloption. - Install the locally built onnxruntime python wheel in
build/<Config>/<Config>/dist/ - Go to test directory:
cd onnxruntime/test/python/quantization - Run all unit tests:
python -m unittest- Or, run a specific unit test file:
python -m unittest test_op_conv_dynamic.py
- Or, run a specific unit test file:
| @@ -60,6 +60,7 @@ | |||
| "Concat": QLinearConcat, | |||
| "Softmax": QLinearSoftmax, | |||
| "Where": QLinearWhere, | |||
| "PRelu": QLinearActivation, | |||
There was a problem hiding this comment.
I believe QLinearActivation would need to be updated to properly handle "PRelu". Onnxruntime doesn't have a QLinearPRelu operator.
Description
Motivation and Context