Change dataset with image size not 28*28, Can't train it. about keras-gan HOT 5 CLOSED

In case you're using the gan_rgb.py code, change this line as well.

X_train = self.get_batch(glob(os.path.join('data', '*.jpg'))[:5000], 28, 28, 'RGB')

from keras-gan.

Thank you, but i have use ccgan and dcgan. How could I fix in those files.

from keras-gan.

Hi. For DCGAN you'll need to change:

model.add(Dense(128 * 7 * 7, activation="relu", input_shape=(self.latent_dim,)))
model.add(Reshape((7, 7, 128)))

to

model.add(Dense(128 * 8 * 8, activation="relu", input_shape=(self.latent_dim,)))
model.add(Reshape((8, 8, 128)))

from keras-gan.

Keras-GAN/aae/adversarial_autoencoder.py
i want to save the model how i can do it

from keras-gan.

Use name_of_your_model.save_weights('name_of_your_model.h5')

from keras-gan.