Open auniquesun opened 2 years ago
Thank you for performing Distributed parallel mechanism and verifying the reported results.
I would love to merge the code once you do the pull request.
@MohamedAfham Since the pull request has not been merged, let me know if you have any concern about this pull request , thank you.
As mentioned here #13 , I'll review the PR as soon as I'm available and get back to you. Sorry for the inconvenience.
The distributed implementation of CrossPoint training and inference is available here !
@MohamedAfham I have succefully integrated the PyTorch DistributedDataParallel mechanism into your codebase, which accelerates the training procedure remarkbly and achieves a similar performance with the paper reported.
Later on I want to pull a request to your repository, thank you.