nets.py 文件源码

def netD(input_images, y, BATCH_SIZE, reuse=False):

   print 'DISCRIMINATOR reuse = '+str(reuse)
   sc = tf.get_variable_scope()
   with tf.variable_scope(sc, reuse=reuse):

      y_dim = int(y.get_shape().as_list()[-1])

      # reshape so it's batchx1x1xy_size
      y = tf.reshape(y, shape=[BATCH_SIZE, 1, 1, y_dim])
      input_ = conv_cond_concat(input_images, y)

      conv1 = tcl.conv2d(input_, 64, 5, 2, activation_fn=tf.identity, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='d_conv1')
      conv1 = lrelu(conv1)

      conv2 = tcl.conv2d(conv1, 128, 5, 2, activation_fn=tf.identity, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='d_conv2')
      conv2 = lrelu(conv2)

      conv3 = tcl.conv2d(conv2, 256, 5, 2, activation_fn=tf.identity, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='d_conv3')
      conv3 = lrelu(conv3)

      conv4 = tcl.conv2d(conv3, 512, 5, 2, activation_fn=tf.identity, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='d_conv4')
      conv4 = lrelu(conv4)

      conv5 = tcl.conv2d(conv4, 1, 4, 1, activation_fn=tf.identity, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='d_conv5')

      print 'input images:',input_images
      print 'conv1:',conv1
      print 'conv2:',conv2
      print 'conv3:',conv3
      print 'conv4:',conv4
      print 'conv5:',conv5
      print 'END D\n'

      tf.add_to_collection('vars', conv1)
      tf.add_to_collection('vars', conv2)
      tf.add_to_collection('vars', conv3)
      tf.add_to_collection('vars', conv4)
      tf.add_to_collection('vars', conv5)

      return conv5