Mauricio A Rovira Galvez

Hello, Ah! I knew it was something obvious. I changed the backbone and I was able to run the model successfully. Thank you for the help!

Hello, I do have another question: whenever I try to train the model using `scripts/train/train_ori.sh`, I get a file not found error like this one: ``` Traceback (most recent call...

I'm closing this issue as my both my original and follow up problems have been solved. Thanks once again for the great work!

# Additional Info The issue can also be reproduced using C++ with ONNXRuntime and the DirectML provider. Through debugging, I've discovered that the issue is coming from the graph fusion...

> I wonder if specifying a lower optimization level like [GraphOptimizationLevel](https://onnxruntime.ai/docs/api/python/api_summary.html#onnxruntime.GraphOptimizationLevel) like `ORT_ENABLE_BASIC` would mitigate the issue until it can be investigated? I've just confirmed that setting the optimisation level...

@fdwr is there any more information I can provide that would help with diagnosing/fixing this?

Here's the output with the debug layer enabled: ``` D3D12 ERROR: An invalid dimension count of 5 was specified in tensor 'A' which is not between 2 and 4. [...

> Would you know if there's an upload on HuggingFace or elsewhere of the direct .onnx model? No, the authors only provide the PTH files. I'll see if I can...

Let me know if there's anything else I can do to help.

@fdwr out of interest: is there a way to track the bug that you opened for DirectML? Related to this: you mentioned that ONNXRuntime should attempt to flatten the leading...