oramasearch / onnx-go

onnx-go gives the ability to import a pre-trained neural network within Go without being linked to a framework or library.
https://blog.owulveryck.info/2019/04/03/from-a-project-to-a-product-the-state-of-onnx-go.html
MIT License
704 stars 72 forks source link

"Asymmetric padding" error #192

Open rivo opened 2 years ago

rivo commented 2 years ago

I'm trying to get an existing model to run but I'm getting the following error message:

onnx: operator conv. Implementation error for attribute pads (1): Asymetric padding

From what I can see, it fails here: https://github.com/owulveryck/onnx-go/blob/12c4d2ede603d7d87a26ad4be469a37a6c38e94b/backend/x/gorgonnx/conv.go#L101

Unfortunately, my familiarity with ONNX and Tensorflow (and I guess ML in general) is very limited so I don't really know what this means. I saw issue #74 which appears to be similar and was resolved but for maxpool, not for conv.

What are my options for making this work?