LLNLanLeN

Results 20 comments of LLNLanLeN

I'm also experience this issue and seem like downgrading to protobuf 3.9 works for me as well

@vv111y I'm not sure if it might help, when I downgrade it to 3.9, it also having the errors, but it resolve itself and actually downgrade the protobuf version. I'm...

awesome. Another possible solution I think is to actually install onnx from source as well, I think that might help.

@quic-ssiddego thank you for getting back to me. Does the AIMET team have a estimated timeline when this feature will be released?

@Silk760 @quic-ssiddego I forgot to reply back to this thread. All of these recommendations are valid point and by the time that I posted this issues, I have already try...

@Silk760 If you can share with me that paper, it would be great. I'm very new to the model compression idea and any resource will be helpful. Thanks 😃

@Silk760 Good luck with your under-review-paper. And I appreciate the feedback so far.

@bomerzz not sure if this is the information you're looking for, but I think the conversion fail because "SiLU" isn't a supported onnx layer: https://github.com/onnx/onnx/blob/main/docs/Operators.md Perhaps you should consider switching...

that is very surprising. Perhaps the C3 layer isn't an actually `nn.Module` layer, which might cause the issue? Unfortunately I don't know how to skip a specific layer. But perhaps...

@TingfengTang Hey, I believe so. According to the video tutorial which you can find in the github repo, the first conv shouldn't be pruned for Channel Pruning. The reason for...