def res_blocks(self, inputs, W_name, b_name):
net = inputs
for res_id in range(self.num_res_block):
res_net = net
for layer_id in range(self.res_block_size):
filter_name = "{}{}_{}".format(W_name, res_id, layer_id)
bias_name = "{}{}_{}".format(b_name, res_id, layer_id)
curr_filter = self.res_filters[filter_name]
curr_bias = self.res_biases[bias_name]
#net = ne.leaky_brelu(net, self.res_leaky_ratio[layer_id], self.layer_low_bound, self.output_up_bound) # Nonlinear act
net = ne.leaky_relu(net, self.res_leaky_ratio[layer_id])
# convolution
net = ne.conv2d_transpose(net,
filters=curr_filter,
biases=curr_bias,
strides=self.res_strides[layer_id],
padding=self.res_padding[layer_id])
net += res_net
if self.use_norm == "BATCH":
net = ne.batch_norm(net, self.is_training)
elif self.use_norm == "LAYER":
net = ne.layer_norm(net, self.is_training)
net = tf.identity(net, name='res_output')
#import pdb; pdb.set_trace()
return net
def in_layer(self, inputs, W_name="W_in_", b_name="b_in_"):
layer_id = 0
net = inputs
filter_name = "{}{}".format(W_name, layer_id)
bias_name = "{}{}".format(b_name, layer_id)
curr_filter = self.in_filter[filter_name]
curr_bias = self.in_bias[bias_name]
# batch normalization
if self.use_norm == "BATCH":
net = ne.batch_norm(net, self.is_training)
elif self.use_norm == "LAYER":
net = ne.layer_norm(net, self.is_training)
elif self.use_norm == "INSTA":
net = ne.instance_norm(net, self.is_training)
#net = ne.leaky_brelu(net, self.conv_leaky_ratio[layer_id], self.layer_low_bound, self.output_up_bound) # Nonlinear act
net = ne.leaky_relu(net, self.in_leaky_ratio)
# convolution
net = ne.conv2d_transpose(net,
filters=curr_filter,
biases=curr_bias,
strides=self.in_stride,
padding=self.in_padding)
#net = ne.max_pool_2x2(net) # Pooling
net = tf.identity(net, name='in_output')
#import pdb; pdb.set_trace()
return net
def _form_groups(net, start_layer, end_layer):
for layer_id in range(start_layer, end_layer):
#res blocks
W_res_name = "W_g{}_res".format(layer_id)
b_res_name = "b_g{}_res".format(layer_id)
net = self.res_blocks(net, W_res_name, b_res_name, scope="RES_{}".format(layer_id))
# decv
filter_name = "{}{}".format(W_name, layer_id)
bias_name = "{}{}".format(b_name, layer_id)
curr_filter = self.decv_filters[filter_name]
curr_bias = self.decv_biases[bias_name]
# de-convolution
net = ne.conv2d_transpose(net,
filters=curr_filter, biases=curr_bias,
strides=self.decv_strides[layer_id],
padding=self.decv_padding[layer_id])
# batch normalization
if self.use_norm == "BATCH":
net = ne.batch_norm(net, self.is_training)
elif self.use_norm == "LAYER":
net = ne.layer_norm(net, self.is_training)
net = ne.leaky_relu(net, self.decv_leaky_ratio[layer_id])
net = ne.drop_out(net, self.decv_drop_rate[layer_id], self.is_training)
return net
def decv_layers(self, inputs, W_name="W_decv", b_name="b_decv"):
net = inputs
for layer_id in range(self.num_decv):
filter_name = "{}{}".format(W_name, layer_id)
bias_name = "{}{}".format(b_name, layer_id)
curr_filter = self.decv_filters[filter_name]
curr_bias = self.decv_biases[bias_name]
# de-convolution
net = ne.conv2d_transpose(net,
out_dim=self.decv_out_dim,
filters=curr_filter,
biases=curr_bias,
strides=self.decv_strides[layer_id],
padding=self.decv_padding[layer_id])
# batch normalization
if self.use_norm == "BATCH":
net = ne.batch_norm(net, self.is_training)
elif self.use_norm == "LAYER":
net = ne.layer_norm(net, self.is_training)
if layer_id == self.num_decv - 1: # last layer
#net = ne.leaky_brelu(net, self.decv_leaky_ratio[layer_id], self.nonlinear_low_bound, self.nonlinear_up_bound) # Nonlinear act
net = ne.leaky_relu(net, self.decv_leaky_ratio[layer_id])
else:
#net = ne.leaky_brelu(net, self.decv_leaky_ratio[layer_id], self.output_low_bound, self.output_up_bound) # Nonlinear act
net = ne.leaky_relu(net, self.decv_leaky_ratio[layer_id])
#net = ne.elu(net)
net = ne.brelu(net, self.output_low_bound,
self.output_up_bound) # clipping the final result
net = tf.identity(net, name='output')
net = tf.reshape(
net, [-1, FLAGS.IMAGE_ROWS, FLAGS.IMAGE_COLS, self.img_channel])
#import pdb; pdb.set_trace()
return net
def decv_layers(self, inputs, W_name="W_decv", b_name="b_decv"):
net = inputs
for layer_id in range(self.num_decv):
filter_name = "{}{}".format(W_name, layer_id)
bias_name = "{}{}".format(b_name, layer_id)
curr_filter = self.decv_filters[filter_name]
curr_bias = self.decv_biases[bias_name]
# de-convolution
net = ne.conv2d_transpose(net,
filters=curr_filter,
biases=curr_bias)
# batch normalization
if self.use_batch_norm:
net = ne.batch_norm(net, self.is_training)
if layer_id == self.num_decv - 1: # last layer
net = ne.leaky_brelu(net, self.decv_leaky_ratio[layer_id],
self.layer_low_bound,
self.layer_up_bound) # Nonlinear act
else:
#net = ne.leaky_brelu(net, self.decv_leaky_ratio[layer_id], self.layer_low_bound, self.layer_up_bound) # Nonlinear act
net = ne.leaky_relu(net, self.decv_leaky_ratio[layer_id])
#net = ne.elu(net)
net = tf.identity(net, name='output')
net = tf.reshape(
net, [-1, FLAGS.IMAGE_ROWS, FLAGS.IMAGE_COLS, FLAGS.NUM_CHANNELS])
#import pdb; pdb.set_trace()
return net
def _form_groups(net, start_layer, end_layer):
for layer_id in range(start_layer, end_layer):
#res blocks
W_res_name = "W_g{}_res".format(layer_id)
b_res_name = "b_g{}_res".format(layer_id)
net = self.res_blocks(net,
W_res_name,
b_res_name,
scope="RES_{}".format(layer_id))
# decv
filter_name = "{}{}".format(W_name, layer_id)
bias_name = "{}{}".format(b_name, layer_id)
curr_filter = self.decv_filters[filter_name]
curr_bias = self.decv_biases[bias_name]
# de-convolution
net = ne.conv2d_transpose(net,
filters=curr_filter,
biases=curr_bias,
strides=self.decv_strides[layer_id],
padding=self.decv_padding[layer_id])
# batch normalization
if self.use_norm == "BATCH":
net = ne.batch_norm(net, self.is_training)
elif self.use_norm == "LAYER":
net = ne.layer_norm(net, self.is_training)
elif self.use_norm == "INSTA":
net = ne.instance_norm(net, self.is_training)
if layer_id != end_layer - 1:
net = ne.leaky_relu(net, self.decv_leaky_ratio[layer_id])
net = ne.drop_out(net, self.decv_drop_rate[layer_id],
self.is_training)
if layer_id == self.num_decv - 2:
# mask
if FLAGS.USE_LABEL_MASK:
w = net.get_shape().as_list()[1]
h = net.get_shape().as_list()[2]
c = net.get_shape().as_list()[3]
net = tf.reshape(net, [-1, w * h, c])
net = tf.matmul(net, mask_states)
net = tf.reshape(net, [-1, w, h, c])
if self.use_norm == "BATCH":
net = ne.batch_norm(net, self.is_training)
elif self.use_norm == "LAYER":
net = ne.layer_norm(net, self.is_training)
elif self.use_norm == "INSTA":
net = ne.instance_norm(net, self.is_training)
#import pdb; pdb.set_trace()
return net
