def _discriminator(self,
input_images,
dims,
train_phase,
activation=tf.nn.relu,
scope_name="discriminator",
scope_reuse=False):
N = len(dims)
with tf.variable_scope(scope_name) as scope:
if scope_reuse:
scope.reuse_variables()
h = input_images
skip_bn = True # First layer of discriminator skips batch norm
for index in range(N - 2):
W = utils.weight_variable([4, 4, dims[index], dims[index + 1]],
name="W_%d" % index)
b = tf.zeros([dims[index + 1]])
h_conv = utils.conv2d_strided(h, W, b)
if skip_bn:
h_bn = h_conv
skip_bn = False
else:
#d_bn = ops.batch_norm(name='d_bn{0}'.format(index))
h_bn = d_bn(h_conv, train=train_phase)
h = activation(h_bn, name="h_%d" % index)
utils.add_activation_summary(h)
W_pred = utils.weight_variable([4, 4, dims[-2], dims[-1]],
name="W_pred")
b = tf.zeros([dims[-1]])
h_pred = utils.conv2d_strided(h, W_pred, b)
return None, h_pred, None # Return the last convolution output. None values are returned to maintatin disc from other GAN
def _discriminator(self, input_images, dims, train_phase, activation=tf.nn.relu, scope_name="discriminator",
scope_reuse=False):
N = len(dims)
with tf.variable_scope(scope_name) as scope:
if scope_reuse:
scope.reuse_variables()
h = input_images
skip_bn = True # First layer of discriminator skips batch norm
for index in range(N - 2):
W = utils.weight_variable([5, 5, dims[index], dims[index + 1]], name="W_%d" % index)
b = utils.bias_variable([dims[index + 1]], name="b_%d" % index)
h_conv = utils.conv2d_strided(h, W, b)
if skip_bn:
h_bn = h_conv
skip_bn = False
else:
h_bn = utils.batch_norm(h_conv, dims[index + 1], train_phase, scope="disc_bn%d" % index)
h = activation(h_bn, name="h_%d" % index)
utils.add_activation_summary(h)
shape = h.get_shape().as_list()
image_size = self.resized_image_size // (2 ** (N - 2)) # dims has input dim and output dim
h_reshaped = tf.reshape(h, [self.batch_size, image_size * image_size * shape[3]])
W_pred = utils.weight_variable([image_size * image_size * shape[3], dims[-1]], name="W_pred")
b_pred = utils.bias_variable([dims[-1]], name="b_pred")
h_pred = tf.matmul(h_reshaped, W_pred) + b_pred
return tf.nn.sigmoid(h_pred), h_pred, h
def subnet1(image, reuse=False):
with tf.variable_scope("subnet1", reuse=reuse):
def _vgg_net(weights, image):
print('setting up vgg model initialized params --> extractor1')
layers = (
'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1',
'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3',
'relu3_3', 'conv3_4', 'relu3_4', 'pool3',
'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3',
'relu4_3', 'conv4_4', 'relu4_4', 'pool4',
'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'conv5_3',
'relu5_3', 'conv5_4', 'relu5_4'
)
net = {}
current = image
for i, name in enumerate(layers):
kind = name[:4]
if kind == 'conv':
kernels, bias = weights[i][0][0][0][0]
# kernels are [width, height, in_channles, out_channles]
# tensorflow are [height, width, in channles, out_channles]
kernels = utils.get_variable(
np.transpose(kernels, (1, 0, 2, 3)), name=name + '_w')
bias = utils.get_variable(bias.reshape(-1), name=name + '_b')
current = utils.conv2d_basic(current, kernels, bias)
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net
model_data = utils.get_model_data("data", MODEL_URL)
weights = np.squeeze(model_data['layers'])
with tf.variable_scope('inference'):
image = tf.reshape(image, [-1, IMAGE_SIZE, IMAGE_SIZE, IMAGE_CHANNLES])
image_net = _vgg_net(weights, image)
conv_final_layer = image_net['relu5_4']
pool5 = utils.max_pool_2x2(conv_final_layer)
W6 = utils.weights_variable([4, 4, 512, 4096], name="W6")
b6 = utils.bias_variable([4096], name='b6')
conv6 = utils.conv2d_strided(pool5, W6, b6, stride=1)
relu6 = tf.nn.relu(conv6, name='relu6')
relu6 = utils.max_pool_2x2(relu6)
disc_out = tf.reshape(relu6, [-1, 4096])
return disc_out
def _discriminator(self,
input_images,
dims,
train_phase,
activation=tf.nn.relu,
scope_name="discriminator",
scope_reuse=False):
N = len(dims)
with tf.variable_scope(scope_name) as scope:
if scope_reuse:
scope.reuse_variables()
h = input_images
skip_bn = True # First layer of discriminator skips batch norm
for index in range(N - 2):
W = utils.weight_variable([4, 4, dims[index], dims[index + 1]],
name="W_%d" % index)
b = tf.zeros([dims[index + 1]])
h_conv = utils.conv2d_strided(h, W, b)
if skip_bn:
h_bn = h_conv
skip_bn = False
else:
# h_bn = tf.contrib.layers.batch_norm(inputs=h_conv, decay=0.9, epsilon=1e-5, is_training=train_phase,
# scope="disc_bn%d" % index)
h_bn = utils.batch_norm("disc_bn%d" % index,
h_conv,
True,
'NHWC',
train_phase,
bn_epsilon=1e-5,
bn_ema=0.9)
# h_bn = utils.batch_norm(h_conv, dims[index + 1], train_phase, scope="disc_bn%d" % index)
h = activation(h_bn, name="h_%d" % index)
utils.add_activation_summary(h)
W_pred = utils.weight_variable([4, 4, dims[-2], dims[-1]],
name="W_pred")
b = tf.zeros([dims[-1]])
h_pred = utils.conv2d_strided(h, W_pred, b)
return None, h_pred, None # Return the last convolution output. None values are returned to maintatin disc from other GAN
