-
Notifications
You must be signed in to change notification settings - Fork 655
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
MPerClassSampler: 'numpy.int32' object is not iterable #611
Comments
Can you try changing |
You have to pass in The reason is that MPerClassSampler is a The It would make more sense for it to be a |
Thank you. Turns out I was distracted by the explicit mention of batch_sampler in the docs for HierarchicalSampler, whereas for MPerClassSampler there is no information on how it is used. Maybe as a quick-fix, this could be clarified in the doc. I'll create a PR later today. |
Hey all. I believe I have found a bug with MPerClassSampler. Using a dataloader which makes use of that sampler throws an exception. As far as I can tell, my HTR code meets all documented preconditions of MPerClassSampler.
My setup:
pytorch_metric_learning.version == "2.1.0"
torch.version == '1.13.1+cu116'
How to reproduce:
The text was updated successfully, but these errors were encountered: