VAEGAN.py generative network output shape doesn't match input to discriminator

crmaximo / VAEGAN

Keras implementation of the paper "Autoencoding beyond pixels using a learned similarity metric"

54 stars 20 forks source link

VAEGAN.py generative network output shape doesn't match input to discriminator #1

Open kristofgiber opened 5 years ago

kristofgiber commented 5 years ago

When running VAEGAN.py, I get shape mismatch error at this line: D_fake, F_fake = D(output)

ValueError: Input 0 of layer dense_3 is incompatible with the layer: expected axis -1 of input shape to have value 4096 but received input with shape [None, 1048576]

yueanga commented 3 years ago

I have the same problem。 have you solved it？ or did you check the input format？