def block_no_sn(x, labels, out_channels, num_classes, is_training, name):
"""Builds the residual blocks used in the generator.
Compared with block, optimized_block always downsamples the spatial resolution
of the input vector by a factor of 4.
Args:
x: The 4D input vector.
labels: The conditional labels in the generation.
out_channels: Number of features in the output layer.
num_classes: Number of classes in the labels.
name: The variable scope name for the block.
Returns:
A `Tensor` representing the output of the operation.
"""
with tf.variable_scope(name):
bn0 = ops.ConditionalBatchNorm(num_classes, name='cbn_0')
bn1 = ops.ConditionalBatchNorm(num_classes, name='cbn_1')
x_0 = x
x = tf.nn.relu(bn0(x, labels, is_training))
x = usample(x)
x = ops.conv2d(x, out_channels, 3, 3, 1, 1, name='conv1')
x = tf.nn.relu(bn1(x, labels, is_training))
x = ops.conv2d(x, out_channels, 3, 3, 1, 1, name='conv2')
x_0 = usample(x_0)
x_0 = ops.conv2d(x_0, out_channels, 1, 1, 1, 1, name='conv3')
return x_0 + x
def block(x, labels, out_channels, num_classes, is_training, CGN, CGN_groups,
name):
with tf.variable_scope(name):
if CGN:
norm0 = ops.ConditionalGroupNorm(num_classes,
CGN_groups,
name='cgn_0')
norm1 = ops.ConditionalGroupNorm(num_classes,
CGN_groups,
name='cgn_1')
else:
norm0 = ops.ConditionalBatchNorm(num_classes, name='cbn_0')
norm1 = ops.ConditionalBatchNorm(num_classes, name='cbn_1')
x_0 = x
x = tf.nn.relu(norm0(x, labels, is_training))
x = usample(x)
x = ops.snconv2d(x, out_channels, 3, 3, 1, 1, name='snconv1')
x = tf.nn.relu(norm1(x, labels, is_training))
x = ops.snconv2d(x, out_channels, 3, 3, 1, 1, name='snconv2')
x_0 = usample(x_0)
x_0 = ops.snconv2d(x_0, out_channels, 1, 1, 1, 1, name='snconv3')
return x_0 + x
def block(x, labels, out_channels, num_classes, is_training, name):
with tf.variable_scope(name):
bn0 = ops.ConditionalBatchNorm(num_classes, name='cbn_0')
bn1 = ops.ConditionalBatchNorm(num_classes, name='cbn_1')
x_0 = x
x = tf.nn.relu(bn0(x, labels, is_training))
x = usample(x)
x = ops.snconv2d(x, out_channels, 3, 3, 1, 1, name='snconv1')
x = tf.nn.relu(bn1(x, labels, is_training))
x = ops.snconv2d(x, out_channels, 3, 3, 1, 1, name='snconv2')
x_0 = usample(x_0)
x_0 = ops.snconv2d(x_0, out_channels, 1, 1, 1, 1, name='snconv3')
return x_0 + x
def class_conditional_generator_block(x, labels, out_channels, num_classes,
is_training, name):
with tf.variable_scope(name):
bn0 = ops.ConditionalBatchNorm(num_classes, name='cbn_0')
bn1 = ops.ConditionalBatchNorm(num_classes, name='cbn_1')
x_0 = x
x = tf.nn.relu(bn0(x, labels, is_training))
x = resnet_architecture.get_conv(x, None, out_channels, "up",
'snconv1', True)
# x = usample(x)
# x = ops.snconv2d(x, out_channels, 3, 3, 1, 1, name='snconv1')
x = tf.nn.relu(bn1(x, labels, is_training))
x = resnet_architecture.get_conv(x, None, out_channels, "none",
'snconv2', True)
# x = ops.snconv2d(x, out_channels, 3, 3, 1, 1, name='snconv2')
x_0 = resnet_architecture.get_conv(x_0, None, out_channels, "up",
'snconv3', True)
# x_0 = usample(x_0)
# x_0 = ops.snconv2d(x_0, out_channels, 1, 1, 1, 1, name='snconv3')
return x_0 + x