MSRF-Net_PyTorch icon indicating copy to clipboard operation
MSRF-Net_PyTorch copied to clipboard

Forget to load pretrained model before testing

Open gudxin opened this issue 2 years ago • 0 comments

Dear amlarraz: There's a little mistake in test.py. Forgetting to load pretrained model before testing. By the way, what's the meaning of class_weights in function CombinedLoss? It seems like a lot influence in computing the loss of model. I got a better result when I tried to delete the class_weights before training the model.

gudxin avatar Mar 04 '22 09:03 gudxin