tutorials
tutorials copied to clipboard
Doubt in the code of autoencoder.py file
Hi Morvan,
Very humbly requesting you to correct my doubt. In the decoding section of your code, you didn't take the transpose of previous weight matrices. Why you did so?
This file: tutorials/tensorflowTUT/tf21_autoencoder/full_code.py
I took transpose of the first two weight matrices to be used in the decoding section.But not getting good results when compared to the result produced by your code( code without transpose of weight matrices)