def conv_generator(x, output_dim, n_filters, scope='Generator'):
with tf.variable_scope(scope):
s4, s2 = int(output_dim / 4), int(output_dim / 2)
z_ = layers.linear(x, s4 * s4 * n_filters * 2)
h0 = tf.reshape(z_, [-1, s4, s4, n_filters * 2])
h1 = layers.convolution2d_transpose(h0, n_filters, [5, 5], stride=2)
h1 = tf.nn.elu(h1)
h2 = layers.convolution2d_transpose(h1, 1, [5, 5], stride=2)
return tf.reshape(tf.nn.tanh(h2), [-1, output_dim * output_dim])
python类convolution2d_transpose()的实例源码
def get_network(self, input_tensor, is_training):
# Load pre-trained inception-resnet model
with slim.arg_scope(inception_resnet_v2_arg_scope(batch_norm_decay = 0.999, weight_decay = 0.0001)):
net, end_points = inception_resnet_v2(input_tensor, is_training = is_training)
# Adding some modification to original InceptionResnetV2 - changing scoring of AUXILIARY TOWER
weight_decay = 0.0005
with tf.variable_scope('NewInceptionResnetV2'):
with tf.variable_scope('AuxiliaryScoring'):
with slim.arg_scope([layers.convolution2d, layers.convolution2d_transpose],
weights_regularizer = slim.l2_regularizer(weight_decay),
biases_regularizer = slim.l2_regularizer(weight_decay),
activation_fn = None):
tf.summary.histogram('Last_layer/activations', net, [KEY_SUMMARIES])
# Scoring
net = slim.dropout(net, 0.7, is_training = is_training, scope = 'Dropout')
net = layers.convolution2d(net, num_outputs = self.FEATURES, kernel_size = 1, stride = 1,
scope = 'Scoring_layer')
feature = net
tf.summary.histogram('Scoring_layer/activations', net, [KEY_SUMMARIES])
# Upsampling
net = layers.convolution2d_transpose(net, num_outputs = 16, kernel_size = 17, stride = 17,
padding = 'VALID', scope = 'Upsampling_layer')
tf.summary.histogram('Upsampling_layer/activations', net, [KEY_SUMMARIES])
# Smoothing layer - separable gaussian filters
net = super()._get_gauss_smoothing_net(net, size = self.SMOOTH_SIZE, std = 1.0, kernel_sum = 0.2)
return net, feature
def netG(z, y, BATCH_SIZE):
# concat attribute y onto z
z = tf.concat([z,y], axis=1)
z = tcl.fully_connected(z, 4*4*512, activation_fn=tf.identity, scope='g_z')
#z = tcl.batch_norm(z)
z = tf.reshape(z, [BATCH_SIZE, 4, 4, 512])
#z = tf.nn.relu(z)
conv1 = tcl.convolution2d_transpose(z, 256, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv1')
conv2 = tcl.convolution2d_transpose(conv1, 128, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv2')
conv3 = tcl.convolution2d_transpose(conv2, 64, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv3')
conv4 = tcl.convolution2d_transpose(conv3, 3, 5, 2, activation_fn=tf.nn.tanh, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv4')
print 'z:',z
print 'conv1:',conv1
print 'conv2:',conv2
print 'conv3:',conv3
print 'conv4:',conv4
print
print 'END G'
print
tf.add_to_collection('vars', z)
tf.add_to_collection('vars', conv1)
tf.add_to_collection('vars', conv2)
tf.add_to_collection('vars', conv3)
tf.add_to_collection('vars', conv4)
return conv4
def netG(z, y, BATCH_SIZE):
# concat attribute y onto z
z = tf.concat([z,y], axis=1)
z = tcl.fully_connected(z, 4*4*512, activation_fn=tf.identity, scope='g_z')
#z = tcl.batch_norm(z)
z = tf.reshape(z, [BATCH_SIZE, 4, 4, 512])
#z = tf.nn.relu(z)
conv1 = tcl.convolution2d_transpose(z, 256, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv1')
conv2 = tcl.convolution2d_transpose(conv1, 128, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv2')
conv3 = tcl.convolution2d_transpose(conv2, 64, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv3')
conv4 = tcl.convolution2d_transpose(conv3, 3, 5, 2, activation_fn=tf.nn.tanh, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv4')
print 'z:',z
print 'conv1:',conv1
print 'conv2:',conv2
print 'conv3:',conv3
print 'conv4:',conv4
print
print 'END G'
print
tf.add_to_collection('vars', z)
tf.add_to_collection('vars', conv1)
tf.add_to_collection('vars', conv2)
tf.add_to_collection('vars', conv3)
tf.add_to_collection('vars', conv4)
return conv4
def netG(z, y, BATCH_SIZE):
# concat attribute y onto z
z = tf.concat([z,y], axis=1)
print 'z:',z
z = tcl.fully_connected(z, 4*4*512, activation_fn=tf.identity, scope='g_z')
z = tf.reshape(z, [BATCH_SIZE, 4, 4, 512])
z = tcl.batch_norm(z)
z = tf.nn.relu(z)
conv1 = tcl.convolution2d_transpose(z, 256, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv1')
conv2 = tcl.convolution2d_transpose(conv1, 128, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv2')
conv3 = tcl.convolution2d_transpose(conv2, 1, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv3')
conv3 = conv3[:,:28,:28,:]
print 'z:',z
print 'conv1:',conv1
print 'conv2:',conv2
print 'conv3:',conv3
print
print 'END G'
print
tf.add_to_collection('vars', z)
tf.add_to_collection('vars', conv1)
tf.add_to_collection('vars', conv2)
tf.add_to_collection('vars', conv3)
return conv3
def deconv2d(input_, o_size, k_size, name='deconv2d'):
print name, 'input', ten_sh(input_)
print name, 'output', o_size
assert np.sum(np.mod(o_size[1:3], ten_sh(input_)[1:3]) - [0,0]) == 0
with tf.variable_scope(name):
init = ly.xavier_initializer_conv2d()
output = ly.convolution2d_transpose(input_, num_outputs=o_size[-1], \
kernel_size=k_size, stride=np.divide(o_size[1:3], ten_sh(input_)[1:3]), \
padding='SAME', weights_initializer=init)
return output
def deconv2d(input_, o_size, k_size, name='deconv2d'):
print name, 'input', ten_sh(input_)
print name, 'output', o_size
assert np.sum(np.mod(o_size[1:3], ten_sh(input_)[1:3]) - [0,0]) == 0
with tf.variable_scope(name):
init = ly.xavier_initializer_conv2d()
output = ly.convolution2d_transpose(input_, num_outputs=o_size[-1], \
kernel_size=k_size, stride=np.divide(o_size[1:3], ten_sh(input_)[1:3]), \
padding='SAME', weights_initializer=init, \
activation_fn=tf.nn.relu, normalizer_fn=ly.batch_norm)
return output
def decoder(layers, y, BATCH_SIZE):
layers = layers[0]
# get all the layers from the encoder for skip connections.
enc_conv1 = layers[0]
enc_conv2 = layers[1]
enc_conv3 = layers[2]
enc_conv4 = layers[3]
enc_conv5 = layers[4]
enc_conv6 = layers[5]
'''
print 'enc_conv1:',enc_conv1
print 'enc_conv2:',enc_conv2
print 'enc_conv3:',enc_conv3
print 'enc_conv4:',enc_conv4
print 'enc_conv5:',enc_conv5
print 'enc_conv6:',enc_conv6
'''
# z is the latent encoding (conv6)
z = tcl.flatten(layers[-1])
z = tf.concat([z,y], axis=1)
print 'z:',z
# reshape z to put through transpose convolutions
s = z.get_shape().as_list()[-1]
z = tf.reshape(z, [BATCH_SIZE, 1, 1, s])
print 'z:',z
dec_conv1 = tcl.convolution2d_transpose(z, 512, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv1')
#dec_conv1 = tf.concat([dec_conv1, enc_conv5], axis=3)
print 'dec_conv1:',dec_conv1
dec_conv2 = tcl.convolution2d_transpose(dec_conv1, 512, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv2')
#dec_conv2 = tf.concat([dec_conv2, enc_conv4], axis=3)
print 'dec_conv2:',dec_conv2
dec_conv3 = tcl.convolution2d_transpose(dec_conv2, 256, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv3')
#dec_conv3 = tf.concat([dec_conv3, enc_conv3], axis=3)
print 'dec_conv3:',dec_conv3
dec_conv4 = tcl.convolution2d_transpose(dec_conv3, 128, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv4')
#dec_conv3 = tf.concat([dec_conv4, enc_conv2], axis=3)
print 'dec_conv4:',dec_conv4
dec_conv5 = tcl.convolution2d_transpose(dec_conv4, 64, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv5')
#dec_conv3 = tf.concat([dec_conv5, enc_conv1], axis=3)
print 'dec_conv5:',dec_conv5
dec_conv6 = tcl.convolution2d_transpose(dec_conv5, 3, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv6')
print 'dec_conv6:',dec_conv6
print
print 'END G'
print
return dec_conv6
