MSRF-Net_PyTorch

MSRF-Net_PyTorch copied to clipboard

RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED when loss.backward() in train.py

3

Thanks for your great work, your code is so much cleaner that I could easily understand. I just had an error raised in train.py when loss.backward(). The error is [RuntimeError:...

chiendoanngoc

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...

gudxin

line 136, in _check_not_importing_main is not going to be frozen to produce an executable.''')

1

Hello, when trying to run your code i keep getting this error, ` ``` Line 136, in _check_not_importing_main is not going to be frozen to produce an executable.''') RuntimeError: An...

TOMSLAUS

About cv2.canny

4

Hello! I have some questions about cv2.canny module. What is the function of "cv2. Canny"module in the figure? This step is not in the MSRF-Net, and I don't see a...

Liqq1

How to define number of classes ?

1

i saw in the train.py : num_classes = 5 Does this consider background as a class? I have a binary segmentation task, should i put num_classes = 2?

TrinhThiBaoAnh