plemeri / UACANet

Official PyTorch implementation of UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation (ACMMM 2021)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Multiple classes training

scpctshp opened this issue · comments

Hi, is it possible to use this model for multi-classes segmentation training? Thanks.

Hello, sorry for the very late reply.
Yes, but you need some modifications. You need to change the output class number from 1 to the desired number, change the loss function for multi-class, change dataloader and custom transform functions.

Also, you can find similar issue from PraNet #9.