a question about gcgan network about keras-gan HOT 9 CLOSED

Hi, thanks! I'm assuming you're referring to DCGAN? If so hopefully all you need to do is change:
model.add(Conv2D(1, kernel_size=3, padding="same"))
to
model.add(Conv2D(self.channels, kernel_size=3, padding="same"))
on line 67.

from keras-gan.

oh yeah dcgan, yes the network works, thanks a lot for your help~~

from keras-gan.

the input dimension for cifar (32) is different from mnist (28), how can it be changed to generate that size?

from keras-gan.

Change
self.img_rows = 28
self.img_cols = 28
self.channels = 1
to
self.img_rows = 32
self.img_rows = 32
self.channels = 3
and also make the changes I suggested in my answer above.

from keras-gan.

thanks for the reply.
i think i also need to modify 'model.add(Dense(128 * 8 * 8))' to make the generator produce 32x32 image, otherwise it produces 28x28. is that expected?

from keras-gan.

Yeah, that is correct. Change these lines:
model.add(Dense(128 * 7 * 7, activation="relu", input_shape=noise_shape))
model.add(Reshape((7, 7, 128)))
to
model.add(Dense(128 * 8 * 8, activation="relu", input_shape=noise_shape))
model.add(Reshape((8, 8, 128)))

from keras-gan.

is there a formula to calculate the layer dimension given an arbitrary input image size? what reference/paper do you use to implement the network?

from keras-gan.

A suggestion I often see is to start with a shallow network, get something that works and then expand on that. There is no recipe when it comes to building the network's architecture that guarantees good results though, and it's extra tricky when it comes to GANs. For this example I build the network based of the architecture in the paper and some experimentation. I can recommend this page: https://github.com/soumith/ganhacks (from one of the authors of DCGAN).

from keras-gan.

thanks for the guide, very helpful. agree on starting with shallow ones that could fit the data first.
excellent work on the implementation!

from keras-gan.