Encoder weights are not updated during the clustering phase

[enaserianhanzaei]

Many thanks for the code.

I have implemented ' Unsupervised Deep Embedding for Clustering Analysis' using Pytorch, and I noticed that the pytorch version is converging much slower than your keras version. By going through the details, I noticed that in your version encoders' weights are not updating during the clustering stage.

I'm not sure what is the reason, but according to the paper, the encoders' weight must get updated.

[enaserianhanzaei]

solved, my bad, I checked the self.encoder instead of self.model.encoder