Deepak Mangla comments

Results 21 comments of


                                            Deepak Mangla

RuntimeError: PyTorch convert function for op 'pythonop' not implemented.

Getting same issue. `RuntimeError: PyTorch convert function for op 'pythonop' not implemented.`

About speed

@lbc402 Did you found out how fast this project is?

Operator requests

Shape operator Reshape should not only be for last layer. [custom_convolution.zip](https://github.com/JDAI-CV/dabnn/files/3489087/custom_convolution.zip)

PyTorch: The kernel appears to have died. It will restart automatically.

I am facing similar problem while using fastai library based on pytorch with cpu only. Anybody found solution?

Can't access symbolic links

Thanks @shirishr, giving full path worked for me.

PowerInfer : using a combination of cpu and gpu for faster Inference

It is designed to improve speed of mainly sparse LLMs. It won't allow faster inference with dense LLMs.

Request help with training

@neuralchen Good progress. Do you think your results might be different because of using different training hyperparameters or data augmentation techniques?

Question for GTEA61 Dataset

@KrisLee512 I am getting same error. I think it requires data rearrangement to run it. Have you found any solution?

expert syncnet loss remains at 0.69 and does not converge

I faced same problem using lrs3 dataset. Haven't found any solution yet. I am surprised that your loss also stuck at 0.69 (same as mine) even though we are using...

How to replace the stable-diffusion-v1-5 model with other SD model

Same question. Anyone able to solve this so far?