search

vicoslab / mixed-segdec-net-comind2021

Official PyTorch implementation for "Mixed supervision for surface-defect detection: from weakly to fully supervised learning"
Other
290 stars 89 forks source link

Question about End2End.py #10

Closed smiura-ai closed 3 years ago

smiura-ai commented 3 years ago

Thank you so much for sharing the scripts.

In line 129 of "End2End.py", "training_iteration()" returns "total_loss_seg + total_loss_dec" instead of "total_loss". Is it supposed to mean something?

JakobBozic commented 3 years ago

Hi, it doesn't mean anything, just a minor bug. I have updated the code to return the total_loss, thank you for bringing this to our attention.