Manu Tom

I increased the dimensions of the final FC layer to a value higher than 1, say 256 and it works

Thanks! Modifiied the criterion as : criterion = CrossEntropy2D().cuda() I added the following class to acw_loss.py class CrossEntropy2D(nn.Module): def __init__(self, weight=None, reduction='mean', ignore_index=255): super(CrossEntropy2D, self).__init__() self.loss = nn.NLLLoss(weight, reduction=reduction, ignore_index=ignore_index)...

kf =0 and k_folder=5 did not automatically create 20% of val set from the train set and threw the following error: ----------creating groundtruth data for training./.val--------------- Traceback (most recent call...

reminder :)

Is there a way to deactivate the val set and use only train and test sets?

If I use test set as val set in the iterative training process, the model will overfit on this val set. What I want is a model trained agnostic of...

>>e.g., train/val 80/20 randomly with 5 folders, then you can train your model with these 5-folder to get 5 best ckpt weights, then you can test your trained 5 ckpt...

I will try with the above. But, I did not understand why you declared the val and test dicts similarly?