`num_workers=batch_size` in function `make_ddp_train_loader()` in dataset/data_loader.py?

zhang-tao-whu / e2ec

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

Other

214 stars 45 forks source link

`num_workers=batch_size` in function `make_ddp_train_loader()` in dataset/data_loader.py? #14

Closed yeshwanth95 closed 1 year ago

yeshwanth95 commented 2 years ago

In the file dataset/data_loader.py, you have set num_workers=batch_size in the function make_ddp_train_loader. Is there any specific reason for this? You mentioned in issue #13 that you've done this for convenience. Can you please elaborate on this?

This looks like it should instead be num_workers=train.cfg.num_workers. Please let me know if this is correct.

Thank you!

zhang-tao-whu commented 2 years ago

Yes, you are right. I will fix the problem.