search

cyclomon / UNSB

Official Repository of "Unpaired Image-to-Image Translation via Neural Schrödinger Bridge" (ICLR 2024)
MIT License
154 stars 5 forks source link

Question about the eval mode in the training forward process #8

Closed QtacierP closed 1 year ago

QtacierP commented 1 year ago

Thank you for sharing this excellent work in the field of unpaired image translation. It introduces a new approach by utilizing SB without any intermediate computation, which is commendable.

However, I have a few questions regarding the details of the training forward process. It appears that you activate the evaluation mode during the training phase.

https://github.com/cyclomon/UNSB/blob/5d22e494a85d5c6aeb64c365c7d92db8b2e01362/models/sb_model.py#L183

Consequently, the normalization layer is never updated throughout the training. I am curious about the rationale behind choosing this strategy.

I appreciate your response in advance.

QtacierP commented 1 year ago

Sorry, I got the answer. It seems like the calculate_NCE_loss method will update the norm layer.