search

cchen-cc / SFDA-DPL

[MICCAI'21] Source-Free domain adaptive fundus image segmentation with denoised pseudo-labeling
51 stars 9 forks source link

why do you use seperated model_eval and model? #5

Closed chenslcool closed 1 year ago

chenslcool commented 1 year ago

In train_target.py, you use model for training and model_eval for testing. However, they only diff in aspp with a BatchNorm. Why do you use different model for training and testing?