Hi there, I’m new to segmentation model.
I would like to use the
My image has shape (256, 256, 3) and my label has shape (256, 256). Each pixel in my label has a class value(0-4). And the batch size set in the DataLoader is 32.
The shape of my input batch is
[32, 3, 256, 256] and the shape of corresponding target is
[32, 256, 256]. I believe this is correct.
I was trying to use
- Is this the correct loss function for my case? Or should I use
- If this is the right one, the output of my model is
[32, 5, 256, 256]. Each image prediction has the shape
[5, 256, 256], does layer 0 means the unnomarlized probabilities of class 0? In order to make a
[32, 256, 256]tensor to match the target to feed into the
BCEWithLogitsLoss, do I need to transform the unnomarlized probabilities to classes?
Thank you everyone.