tuna2134/sbv2-v2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Add: test code for CoreMLExecutionProvider on a trial basis

Browse Source 
Currently ONNXRuntime's CoreML support is not very good, and on my environment, I get errors like “coreml_execution_provider.cc:192 operator() Input (/sdp/flows.3/GatherND_2_output_0) has a dynamic shape ({-1,-1}) but the runtime shape ({0,10}) has zero elements. This is not supported by the CoreML EP.” and inference fails.
I hope this will be fixed in a future version of ONNXRuntime, and leave the test code as it is.
This commit is contained in:
tsukumi
2024-09-23 21:07:27 +09:00
parent b67e50fd8d
commit d935d30e4c
4 changed files with 17 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pyproject.toml
View File

@@ -109,6 +109,8 @@ test = "pytest -s tests/test_main.py::test_synthesize_onnx_cpu"
test-cuda = "pytest -s tests/test_main.py::test_synthesize_onnx_cuda"
# Usage: `hatch run test-onnx:test-directml`
test-directml = "pytest -s tests/test_main.py::test_synthesize_onnx_directml"
# Usage: `hatch run test-onnx:test-coreml`
test-coreml = "pytest -s tests/test_main.py::test_synthesize_onnx_coreml"
# Usage: `hatch run test-onnx:coverage`
test-cov = "coverage run -m pytest -s tests/test_main.py::test_synthesize_onnx_cpu"
# Usage: `hatch run test-onnx:cov-report`