hjweide / adversarial-autoencoder Goto Github PK

My way to solve this TypeError is rewriting the function of get_output_shape_for in Class ConCatLayer, compatibility with summarizing while None in sizes . But rewriting package's function seems a little tricky. @hjweide , how did you do?

Hi hjweide,
Thank you very much for the code. I am new to Theano and couldn't get my environment setup to run your code. However my question is, have you been able to reach an error rate of 1.90 (±0:10)% for MNIST 100 labels (as reported in original paper)? Even after 5000 epochs the lowest I get is somewhat around 5% (in my TensorFlow implementation).