BloodAxe/Catalyst-Inria-Segmentation-Example

Dataloader in PyTorch

xdtl opened this issue 3 years ago · 2 comments

xdtl commented 3 years ago

This may affect data augmentation: https://tanelp.github.io/posts/a-bug-that-plagues-thousands-of-open-source-ml-projects/

BloodAxe commented 3 years ago

This repo is not affected by a well-known behavior of np.random under multiprocessing in python.

xdtl commented 3 years ago

It's good to know that. Thanks!