GAN Ändern der Eingangsgröße verursacht Fehler

Question

Unten Code nimmt nur 32 * 32 Eingang, ich möchte 128 * 128 Bilder einspeisen, wie man darüber geht. Der Code aus dem Tutorial ist - https://github.com/awjuliani/TF-Tutorials/blob/master/DCGAN.ipynb

def Generator (z):

zP = slim.fully_connected(z,4*4*256,normalizer_fn=slim.batch_norm,\ 
    activation_fn=tf.nn.relu,scope='g_project',weights_initializer=initializer) 
zCon = tf.reshape(zP,[-1,4,4,256]) 

gen1 = slim.convolution2d_transpose(\ 
    zCon,num_outputs=64,kernel_size=[5,5],stride=[2,2],\ 
    padding="SAME",normalizer_fn=slim.batch_norm,\ 
    activation_fn=tf.nn.relu,scope='g_conv1', weights_initializer=initializer) 

gen2 = slim.convolution2d_transpose(\ 
    gen1,num_outputs=32,kernel_size=[5,5],stride=[2,2],\ 
    padding="SAME",normalizer_fn=slim.batch_norm,\ 
    activation_fn=tf.nn.relu,scope='g_conv2', weights_initializer=initializer) 

gen3 = slim.convolution2d_transpose(\ 
    gen2,num_outputs=16,kernel_size=[5,5],stride=[2,2],\ 
    padding="SAME",normalizer_fn=slim.batch_norm,\ 
    activation_fn=tf.nn.relu,scope='g_conv3', weights_initializer=initializer) 

g_out = slim.convolution2d_transpose(\ 
    gen3,num_outputs=1,kernel_size=[32,32],padding="SAME",\ 
    biases_initializer=None,activation_fn=tf.nn.tanh,\ 
    scope='g_out', weights_initializer=initializer) 

return g_out 

def Scheider (unten, Wiederverwendung = False):

dis1 = slim.convolution2d(bottom,16,[4,4],stride=[2,2],padding="SAME",\ 
    biases_initializer=None,activation_fn=lrelu,\ 
    reuse=reuse,scope='d_conv1',weights_initializer=initializer) 

dis2 = slim.convolution2d(dis1,32,[4,4],stride=[2,2],padding="SAME",\ 
    normalizer_fn=slim.batch_norm,activation_fn=lrelu,\ 
    reuse=reuse,scope='d_conv2', weights_initializer=initializer) 

dis3 = slim.convolution2d(dis2,64,[4,4],stride=[2,2],padding="SAME",\ 
    normalizer_fn=slim.batch_norm,activation_fn=lrelu,\ 
    reuse=reuse,scope='d_conv3',weights_initializer=initializer) 

d_out = slim.fully_connected(slim.flatten(dis3),1,activation_fn=tf.nn.sigmoid,\ 
    reuse=reuse,scope='d_out', weights_initializer=initializer) 

return d_out 

Unten ist der Fehler, die ich erhalte, wenn Ich füttere 128 * 128 Bilder.

Trying to share variable d_out/weights, but specified shape (1024, 1) and found shape (16384, 1). 

Answer 1

Der Generator erzeugt 32 * 32 Bilder, und wenn wir also jede andere Dimension im Diskriminator einspeisen, führt dies zu dem angegebenen Fehler.

Die Lösung besteht darin, 128 * 128 Bilder vom Generator zu erzeugen, indem 1. Hinzufügen mehr nein. der Schichten (2 in diesem Fall) 2. Ändern der Eingang zum Generator

zP = slim.fully_connected(z,16*16*256,normalizer_fn=slim.batch_norm,\ 
activation_fn=tf.nn.relu,scope='g_project',weights_initializer=initializer) 
zCon = tf.reshape(zP,[-1,16,16,256])