def block(x, res): # res = 2..resolution_log2
t = x
with tf.variable_scope('Conv0'):
x = apply_bias_act(modulated_conv2d_layer(x,
dlabel,
fmaps=nf(res - 1),
kernel=3),
act=act)
with tf.variable_scope('Conv1_down'):
x = apply_bias_act(modulated_conv2d_layer(
x,
dlabel,
fmaps=nf(res - 2),
kernel=3,
down=True,
resample_kernel=resample_kernel),
act=act)
if architecture == 'resnet':
with tf.variable_scope('Skip'):
t = conv2d_layer(t,
fmaps=nf(res - 2),
kernel=1,
down=True,
resample_kernel=resample_kernel)
x = (x + t) * (1 / np.sqrt(2))
return x
def fromrgb(x, y, res): # res = 2..resolution_log2
with tf.variable_scope('FromRGB'):
t = apply_bias_act(modulated_conv2d_layer(y,
dlabel,
fmaps=nf(res - 1),
kernel=1),
act=act)
return t if x is None else x + t
def layer(x, layer_idx, fmaps, kernel, up=False):
x = modulated_conv2d_layer(x, dlatents_in[:, layer_idx], fmaps=fmaps, kernel=kernel, up=up, resample_kernel=resample_kernel, fused_modconv=fused_modconv)
if randomize_noise:
noise = tf.random_normal([tf.shape(x)[0], 1, x.shape[2], x.shape[3]], dtype=x.dtype)
else:
noise = tf.cast(noise_inputs[layer_idx], x.dtype)
noise_strength = tf.get_variable('noise_strength', shape=[], initializer=tf.initializers.zeros())
x += noise * tf.cast(noise_strength, x.dtype)
return apply_bias_act(x, act=act)
def torgb(res, x): # res = 2..resolution_log2
with tf.variable_scope('ToRGB_lod%d' % (resolution_log2 - res)):
return apply_bias_act(
modulated_conv2d_layer(x,
dlatents_in[:, res * 2 - 3],
fmaps=num_channels,
kernel=1,
demodulate=False,
fused_modconv=fused_modconv))
def torgb(x, y, res): # res = 2..resolution_log2
with tf.variable_scope('ToRGB'):
t = apply_bias_act(
modulated_conv2d_layer(x,
dlatents_in[:, res * 2 - 3],
fmaps=num_channels,
kernel=1,
demodulate=False,
fused_modconv=fused_modconv))
return t if y is None else y + t
def D_stylegan2(
images_in, # First input: Images [minibatch, channel, height, width].
labels_in, # Second input: Labels [minibatch, label_size].
num_channels = 3, # Number of input color channels. Overridden based on dataset.
resolution = 512, # Input resolution. Overridden based on dataset.
label_size = 127, # Dimensionality of the labels, 0 if no labels. Overridden based on dataset.
fmap_base = 16 << 10, # Overall multiplier for the number of feature maps.
fmap_decay = 1.0, # log2 feature map reduction when doubling the resolution.
fmap_min = 1, # Minimum number of feature maps in any layer.
fmap_max = 512, # Maximum number of feature maps in any layer.
architecture = 'resnet', # Architecture: 'orig', 'skip', 'resnet'.
nonlinearity = 'lrelu', # Activation function: 'relu', 'lrelu', etc.
mbstd_group_size = 4, # Group size for the minibatch standard deviation layer, 0 = disable.
mbstd_num_features = 1, # Number of features for the minibatch standard deviation layer.
dtype = 'float32', # Data type to use for activations and outputs.
resample_kernel = [1, 3, 3, 1], # Low-pass filter to apply when resampling activations. None = no filtering.
**_kwargs): # Ignore unrecognized keyword args.
resolution_log2 = int(np.log2(resolution))
assert resolution == 2**resolution_log2 and resolution >= 4
def nf(stage): return np.clip(int(fmap_base / (2.0 ** (stage * fmap_decay))), fmap_min, fmap_max)
assert architecture in ['orig', 'skip', 'resnet']
act = nonlinearity
images_in.set_shape([None, num_channels, resolution, resolution])
labels_in.set_shape([None, label_size])
images_in = tf.cast(images_in, dtype)
labels_in = tf.cast(labels_in, dtype)
dlabel = D_mapping_label(labels_in=labels_in, label_size=label_size)
dlabel = tf.cast(dlabel, dtype)
# Building blocks for main layers.
def fromrgb(x, y, res): # res = 2..resolution_log2
with tf.variable_scope('FromRGB'):
t = apply_bias_act(modulated_conv2d_layer(y, dlabel, fmaps=nf(res-1), kernel=1), act=act)
return t if x is None else x + t
def block(x, res): # res = 2..resolution_log2
t = x
with tf.variable_scope('Conv0'):
x = apply_bias_act(modulated_conv2d_layer(x, dlabel, fmaps=nf(res-1), kernel=3), act=act)
with tf.variable_scope('Conv1_down'):
x = apply_bias_act(modulated_conv2d_layer(x, dlabel, fmaps=nf(res-2), kernel=3, down=True, resample_kernel=resample_kernel), act=act)
if architecture == 'resnet':
with tf.variable_scope('Skip'):
t = conv2d_layer(t, fmaps=nf(res-2), kernel=1, down=True, resample_kernel=resample_kernel)
x = (x + t) * (1 / np.sqrt(2))
return x
def downsample(y):
with tf.variable_scope('Downsample'):
return downsample_2d(y, k=resample_kernel)
feature_maps = []
# Main layers.
x = None
y = images_in
for res in range(resolution_log2, 2, -1):
with tf.variable_scope('%dx%d' % (2**res, 2**res)):
if architecture == 'skip' or res == resolution_log2:
x = fromrgb(x, y, res)
feature_maps.append(x)
x = block(x, res)
if architecture == 'skip':
y = downsample(y)
feature_maps.append(x)
# Final layers.
with tf.variable_scope('4x4'):
if architecture == 'skip':
x = fromrgb(x, y, 2)
if mbstd_group_size > 1:
with tf.variable_scope('MinibatchStddev'):
x = minibatch_stddev_layer(x, mbstd_group_size, mbstd_num_features)
with tf.variable_scope('Conv'):
x = apply_bias_act(modulated_conv2d_layer(x, dlabel, fmaps=nf(1), kernel=3), act=act)
with tf.variable_scope('Dense0'):
x = apply_bias_act(dense_layer(x, fmaps=nf(0)), act=act)
# Output layer with label conditioning from "Which Training Methods for GANs do actually Converge?"
with tf.variable_scope('Output'):
x = apply_bias_act(dense_layer(x, fmaps=max(labels_in.shape[1], 1)))
if labels_in.shape[1] > 0:
x = tf.reduce_sum(x * labels_in, axis=1, keepdims=True)
scores_out = x
# Output.
assert scores_out.dtype == tf.as_dtype(dtype)
scores_out = tf.identity(scores_out, name='scores_out')
feature_maps_0 = tf.identity(feature_maps[0], name='feature_maps_0')
feature_maps_1 = tf.identity(feature_maps[1], name='feature_maps_1')
feature_maps_2 = tf.identity(feature_maps[2], name='feature_maps_2')
feature_maps_3 = tf.identity(feature_maps[3], name='feature_maps_3')
feature_maps_4 = tf.identity(feature_maps[4], name='feature_maps_4')
feature_maps_5 = tf.identity(feature_maps[5], name='feature_maps_5')
feature_maps_6 = tf.identity(feature_maps[6], name='feature_maps_6')
feature_maps_7 = tf.identity(feature_maps[7], name='feature_maps_7')
return scores_out, feature_maps_0, feature_maps_1, feature_maps_2, feature_maps_3, feature_maps_4, feature_maps_5, feature_maps_6, feature_maps_7
