aakash-saboo

Error in Generalized contrastive loss

5

Hi. Thank you so much for your work and its implementation. I have been trying to evaluate generalized contrastive loss between random normal vectors. The code works for small batches...

memory consumption too high

1

Hi First of all, I really liked the paper and the implementation. but when i ran it for VGG19 network, it took almost 10.5GB of GPU RAM( I have 1...

Is the code written only for nn.NLLL() loss?

3

I changed the loss to MultLabelSoftMargin classifier. My input is a regular 4 dimension image array and targets are one hot encoded vectors(with vector length = n_classes). I am performing...

ValueError: bad marshal data (unknown type code) with tensorflow 1.4.0,keras 2.2.1 and python 3.5.2

1

 This is the error i get when testing the code. I am using the specified version of libraries as mentioned in the segmentation template.

ValueError: vec Nan

2

Hi I was training a GAN using the optimizer. It runs fine for 80 iterations but on 81st iteration, it gave ValueError: vec Nan.  Can you suggest me a...

@dongliangcao Hi. I am training the model on a different dataset of cortical surfaces. The magnitudes of the losses are very high, of the order of 10^8. I am overfitting...