def semantic2visual_2d(semantic_feat,
semantic_size,
visual_size,
name='default',
reuse=False,
dropout=False,
keep_prob=1.0,
activation='leaky_relu'):
assert activation == 'leaky_relu'
with tf.variable_scope('semantic2visual_2d_%s' % (name),
reuse=reuse) as vs:
assert semantic_feat.get_shape().as_list()[-2:] == [
semantic_size, semantic_size
]
reshape_semantic_feat = tf.reshape(semantic_feat,
[-1, semantic_size * semantic_size],
name='reshape_semantic_feat')
if dropout:
reshape_semantic_feat = tf.nn.dropout(
reshape_semantic_feat,
keep_prob,
name='reshape_semantic_feat_dropout')
map2 = leaky_relu(
fc(reshape_semantic_feat, semantic_size, biased=True, name='map2'))
if dropout:
map2 = tf.nn.dropout(map2, keep_prob, name='map2_dropout')
visual_feat = leaky_relu(
fc(map2, visual_size, biased=True, name='map1'))
variables = tf.contrib.framework.get_variables(vs)
return visual_feat, variables
def discriminator_cycle(vector, name='vector', reuse=False):
semantic_size = vector.get_shape().as_list()[-1]
with tf.variable_scope('discriminator_%s' % (name), reuse=reuse) as vs:
fc1 = leaky_relu(
fc(vector, semantic_size, name='fc1', biased=True,
trainable=False))
output = fc(fc1, 1, name='output', biased=True, trainable=False)
variables = tf.contrib.framework.get_variables(vs)
return output, variables
def comparator_caffenet_fc7(input_image, reuse=False, trainable=False):
with tf.variable_scope('comparator', reuse=reuse) as vs:
# input_image = tf.placeholder(tf.float32, shape=(None, 227, 227, 3), name='input_image')
assert input_image.get_shape().as_list()[1:] == [227, 227, 3]
relu1 = relu(
conv(input_image,
11,
11,
96,
4,
4,
pad='VALID',
name='conv1',
trainable=trainable))
pool1 = max_pool(relu1, 3, 3, 2, 2, pad='VALID', name='pool1')
norm1 = lrn(pool1, 2, 2e-05, 0.75, name='norm1')
relu2 = relu(
conv(norm1,
5,
5,
256,
1,
1,
group=2,
name='conv2',
trainable=trainable))
pool2 = max_pool(relu2, 3, 3, 2, 2, pad='VALID', name='pool2')
norm2 = lrn(pool2, 2, 2e-05, 0.75, name='norm2')
relu3 = relu(
conv(norm2, 3, 3, 384, 1, 1, name='conv3', trainable=trainable))
relu4 = relu(
conv(relu3,
3,
3,
384,
1,
1,
group=2,
name='conv4',
trainable=trainable))
relu5 = relu(
conv(relu4,
3,
3,
256,
1,
1,
group=2,
name='conv5',
trainable=trainable))
pool5 = max_pool(relu5, 3, 3, 2, 2, pad='VALID', name='pool5')
fc6 = relu(fc(pool5, 4096, name='fc6', trainable=trainable))
fc7 = relu(fc(fc6, 4096, name='fc7', trainable=trainable))
variables = tf.contrib.framework.get_variables(vs)
return fc7, variables
def discriminator_image(input_image,
real_input_label,
fake_input_label,
num_train_classes,
name='image',
reuse=False):
with tf.variable_scope('discriminator_%s' % (name), reuse=reuse) as vs:
dconv1 = relu(
conv(input_image, 7, 7, 32, 4, 4, pad='VALID', name='dconv1'))
dconv2 = relu(conv(dconv1, 5, 5, 64, 1, 1, pad='VALID', name='dconv2'))
dconv3 = relu(conv(dconv2, 3, 3, 128, 2, 2, pad='VALID',
name='dconv3'))
dconv4 = relu(conv(dconv3, 3, 3, 256, 1, 1, pad='VALID',
name='dconv4'))
dconv5 = relu(conv(dconv4, 3, 3, 256, 2, 2, pad='VALID',
name='dconv5'))
dpool5 = avg_pool(dconv5, 11, 11, 11, 11, name='dpool5')
dpool5_reshape = tf.reshape(dpool5, [-1, 256], name='dpool5_reshape')
# label information
real_label_feat = tf.one_hot(real_input_label, depth=num_train_classes)
fake_label_feat = tf.one_hot(fake_input_label, depth=num_train_classes)
label_feat = tf.concat([real_label_feat, fake_label_feat], axis=0)
# SAVE GPU MEMORY
Ffc1 = relu(fc(label_feat, 128, name='Ffc1'))
Ffc2 = relu(fc(Ffc1, 128, name='Ffc2'))
concat5 = tf.concat([dpool5_reshape, Ffc2], axis=1, name='concat5')
drop5 = tf.nn.dropout(concat5, keep_prob=0.5, name='drop5')
# SAVE GPU MEMORY
dfc6 = relu(fc(drop5, 256, name='dfc6'))
dfc7 = fc(dfc6, 1, name='dfc7')
variables = tf.contrib.framework.get_variables(vs)
return dfc7, variables
def semantic2semantic_2layer(semantic_feat,
semantic_size,
name='default',
reuse=False,
dropout=False,
keep_prob=1.0,
activation='leaky_relu'):
assert activation == 'leaky_relu'
with tf.variable_scope('semantic2semantic_2layer_%s' % (name),
reuse=reuse) as vs:
# assert semantic_feat.get_shape().as_list()[-1] == semantic_size
if dropout:
semantic_feat = tf.nn.dropout(semantic_feat,
keep_prob,
name='semantic_feat_dropout')
map1 = leaky_relu(
fc(semantic_feat, semantic_size, biased=True, name='map1'))
if dropout:
map1 = tf.nn.dropout(map1, keep_prob, name='map1_dropout')
ret_semantic_feat = leaky_relu(
fc(map1, semantic_size, biased=True, name='ret_semantic_feat'))
variables = tf.contrib.framework.get_variables(vs)
return ret_semantic_feat, variables
def classifier_caffenet(input_image,
output,
reuse=False,
trainable=False,
dropout=False,
keep_prob=1.0):
with tf.variable_scope('classifier', reuse=reuse) as vs:
# input_image = tf.placeholder(tf.float32, shape=(None, 227, 227, 3), name='input_image')
# assert input_image.get_shape().as_list()[1:] == [227, 227, 3]
relu1 = relu(
conv(input_image,
11,
11,
96,
4,
4,
pad='VALID',
name='conv1',
trainable=trainable))
pool1 = max_pool(relu1, 3, 3, 2, 2, pad='VALID', name='pool1')
norm1 = lrn(pool1, 2, 2e-05, 0.75, name='norm1')
relu2 = relu(
conv(norm1,
5,
5,
256,
1,
1,
group=2,
name='conv2',
trainable=trainable))
pool2 = max_pool(relu2, 3, 3, 2, 2, pad='VALID', name='pool2')
norm2 = lrn(pool2, 2, 2e-05, 0.75, name='norm2')
relu3 = relu(
conv(norm2, 3, 3, 384, 1, 1, name='conv3', trainable=trainable))
relu4 = relu(
conv(relu3,
3,
3,
384,
1,
1,
group=2,
name='conv4',
trainable=trainable))
relu5 = relu(
conv(relu4,
3,
3,
256,
1,
1,
group=2,
name='conv5',
trainable=trainable))
pool5 = max_pool(relu5, 3, 3, 2, 2, pad='VALID', name='pool5')
fc6 = relu(fc(pool5, 4096, name='fc6', trainable=trainable))
if dropout:
fc6 = tf.nn.dropout(fc6, keep_prob=keep_prob)
fc7 = relu(fc(fc6, 4096, name='fc7', trainable=trainable))
if dropout:
fc7 = tf.nn.dropout(fc7, keep_prob=keep_prob)
fc8 = fc(fc7, output, name='output', trainable=trainable)
variables = tf.contrib.framework.get_variables(vs)
return fc8, variables
def generator_caffenet_fc6(input_feat, reuse=False, trainable=False):
with tf.variable_scope('generator', reuse=reuse) as vs:
assert input_feat.get_shape().as_list()[-1] == 4096
# input_feat = tf.placeholder(tf.float32, shape=(None, 4096), name='feat')
relu_defc7 = leaky_relu(
fc(input_feat, 4096, name='defc7', trainable=trainable))
relu_defc6 = leaky_relu(
fc(relu_defc7, 4096, name='defc6', trainable=trainable))
relu_defc5 = leaky_relu(
fc(relu_defc6, 4096, name='defc5', trainable=trainable))
reshaped_defc5 = tf.reshape(relu_defc5, [-1, 256, 4, 4])
relu_deconv5 = leaky_relu(
upconv(tf.transpose(reshaped_defc5, perm=[0, 2, 3, 1]),
256,
4,
2,
'deconv5',
biased=True,
trainable=trainable))
relu_conv5_1 = leaky_relu(
upconv(relu_deconv5,
512,
3,
1,
'conv5_1',
biased=True,
trainable=trainable))
relu_deconv4 = leaky_relu(
upconv(relu_conv5_1,
256,
4,
2,
'deconv4',
biased=True,
trainable=trainable))
relu_conv4_1 = leaky_relu(
upconv(relu_deconv4,
256,
3,
1,
'conv4_1',
biased=True,
trainable=trainable))
relu_deconv3 = leaky_relu(
upconv(relu_conv4_1,
128,
4,
2,
'deconv3',
biased=True,
trainable=trainable))
relu_conv3_1 = leaky_relu(
upconv(relu_deconv3,
128,
3,
1,
'conv3_1',
biased=True,
trainable=trainable))
deconv2 = leaky_relu(
upconv(relu_conv3_1,
64,
4,
2,
'deconv2',
biased=True,
trainable=trainable))
deconv1 = leaky_relu(
upconv(deconv2,
32,
4,
2,
'deconv1',
biased=True,
trainable=trainable))
deconv0 = upconv(deconv1,
3,
4,
2,
'deconv0',
biased=True,
trainable=trainable)
variables = tf.contrib.framework.get_variables(vs)
return deconv0, variables
