How it works with Batch Normalization?

SimonVandenhende / Multi-Task-Learning-PyTorch

PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).

Other

780 stars 113 forks source link

How it works with Batch Normalization? #28

Open kellenf opened 1 year ago

kellenf commented 1 year ago

Using dataloader by dataloader, sometimes memory is limited, so only little batch for each dataloader. It will disadvantage the performance of batch normalization? how to fix this problem?