How can I get Features extracted by encoder


(Muhammad Furqan Rafique) #1

How i can create dataset of feature that my autoencoder learns or in other words where is the dataset reduce by encoder?


#2

Would you like to save the features learned by the encoder?
Depending on the model, you could return the latent vectors with the final output and just concatenate them into a tensor, and save them using torch.save.


(Muhammad Furqan Rafique) #3

Yes, I am trying to save the features learned by the encoder. Thanks for the answer.