Contractive_Autoencoder_in_Pytorch icon indicating copy to clipboard operation
Contractive_Autoencoder_in_Pytorch copied to clipboard

verified publisher icon avijit9
→

Metadata

Pytorch implementation of contractive autoencoder on MNIST dataset

Results 1 Contractive_Autoencoder_in_Pytorch issues
Sort by recently updated
recently updated
newest added

bug; the CAE penalty is incorrect for any non-sigmoid activation

4 comment

The CAE class uses the relu nonlinearity. https://github.com/avijit9/Contractive_Autoencoder_in_Pytorch/blob/master/CAE_pytorch.py#L61 However, the way the CAE loss is computed is only valid for sigmoid activations. This is easy enough to show: the derivative...

Sycor4x avatar Sycor4x

← Metadata

53
Stars
17
Forks
Watchers

Owner

verified publisher icon avijit9

Metadata

Pytorch implementation of contractive autoencoder on MNIST dataset

Back