Open jlami opened 2 months ago
Setting ep.dml.disable_graph_fusion
to 1 while enabling the Split op again also gives correct results, so I guess the problem is in the DmlGraphFusionTransformer
@smk2007
This issue has been automatically marked as stale due to inactivity and will be closed in 30 days if no further activity occurs. If further support is needed, please provide an update and/or more details.
Is there anything I can do to help with this issue? Or do you have any pointers as to where I could look myself. I could not really make any sense of the graph fusion yet, so any pointers are welcome.
Describe the issue
Running the htdemucs model on DML gives incorrect results compared to the CPU execution.
To reproduce
The model we are using is the htdemucs v4 model from here: https://github.com/facebookresearch/demucs
You can find a converted onnx model in this zip: https://github.com/intel/openvino-plugins-ai-audacity/releases/download/v3.4.2-R1/openvino-models.zip (2GB zip, htdemucs_v4.onnx itself is 170MB)
If I comment out this line, DML gives correct results: https://github.com/microsoft/onnxruntime/blob/74028e4bdcfa3069113b657bc1e2f32389372dfa/onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/OperatorRegistration.cpp#L782
Urgency
No response
Platform
Windows
OS Version
10
ONNX Runtime Installation
Built from Source
ONNX Runtime Version or Commit ID
74028e4bdcfa3069113b657bc1e2f32389372dfa
ONNX Runtime API
C
Architecture
X64
Execution Provider
DirectML
Execution Provider Library Version
1.14