def generator(z, train_mode):
with tf.variable_scope("generator") as scope:
W_0 = utils.weight_variable([FLAGS.z_dim, 64 * GEN_DIMENSION / 2 * IMAGE_SIZE / 16 * IMAGE_SIZE / 16],
name="W_0")
b_0 = utils.bias_variable([64 * GEN_DIMENSION / 2 * IMAGE_SIZE / 16 * IMAGE_SIZE / 16], name="b_0")
z_0 = tf.matmul(z, W_0) + b_0
h_0 = tf.reshape(z_0, [-1, IMAGE_SIZE / 16, IMAGE_SIZE / 16, 64 * GEN_DIMENSION / 2])
h_bn0 = utils.batch_norm(h_0, 64 * GEN_DIMENSION / 2, train_mode, scope="gen_bn0")
h_relu0 = tf.nn.relu(h_bn0, name='relu0')
utils.add_activation_summary(h_relu0)
# W_1 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION/2, 64 * GEN_DIMENSION], name="W_1")
# b_1 = utils.bias_variable([64 * GEN_DIMENSION/2], name="b_1")
# deconv_shape = tf.pack([tf.shape(h_relu0)[0], IMAGE_SIZE / 16, IMAGE_SIZE / 16, 64 * GEN_DIMENSION/2])
# h_conv_t1 = utils.conv2d_transpose_strided(h_relu0, W_1, b_1, output_shape=deconv_shape)
# h_bn1 = utils.batch_norm(h_conv_t1, 64 * GEN_DIMENSION/2, train_mode, scope="gen_bn1")
# h_relu1 = tf.nn.relu(h_bn1, name='relu1')
# utils.add_activation_summary(h_relu1)
W_2 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION / 4, 64 * GEN_DIMENSION / 2],
name="W_2")
b_2 = utils.bias_variable([64 * GEN_DIMENSION / 4], name="b_2")
deconv_shape = tf.pack([tf.shape(h_relu0)[0], IMAGE_SIZE / 8, IMAGE_SIZE / 8, 64 * GEN_DIMENSION / 4])
h_conv_t2 = utils.conv2d_transpose_strided(h_relu0, W_2, b_2, output_shape=deconv_shape)
h_bn2 = utils.batch_norm(h_conv_t2, 64 * GEN_DIMENSION / 4, train_mode, scope="gen_bn2")
h_relu2 = tf.nn.relu(h_bn2, name='relu2')
utils.add_activation_summary(h_relu2)
W_3 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION / 8, 64 * GEN_DIMENSION / 4],
name="W_3")
b_3 = utils.bias_variable([64 * GEN_DIMENSION / 8], name="b_3")
deconv_shape = tf.pack([tf.shape(h_relu2)[0], IMAGE_SIZE / 4, IMAGE_SIZE / 4, 64 * GEN_DIMENSION / 8])
h_conv_t3 = utils.conv2d_transpose_strided(h_relu2, W_3, b_3, output_shape=deconv_shape)
h_bn3 = utils.batch_norm(h_conv_t3, 64 * GEN_DIMENSION / 8, train_mode, scope="gen_bn3")
h_relu3 = tf.nn.relu(h_bn3, name='relu3')
utils.add_activation_summary(h_relu3)
W_4 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION / 16, 64 * GEN_DIMENSION / 8],
name="W_4")
b_4 = utils.bias_variable([64 * GEN_DIMENSION / 16], name="b_4")
deconv_shape = tf.pack([tf.shape(h_relu3)[0], IMAGE_SIZE / 2, IMAGE_SIZE / 2, 64 * GEN_DIMENSION / 16])
h_conv_t4 = utils.conv2d_transpose_strided(h_relu3, W_4, b_4, output_shape=deconv_shape)
h_bn4 = utils.batch_norm(h_conv_t4, 64 * GEN_DIMENSION / 16, train_mode, scope="gen_bn4")
h_relu4 = tf.nn.relu(h_bn4, name='relu4')
utils.add_activation_summary(h_relu4)
W_5 = utils.weight_variable([5, 5, NUM_OF_CHANNELS, 64 * GEN_DIMENSION / 16], name="W_5")
b_5 = utils.bias_variable([NUM_OF_CHANNELS], name="b_5")
deconv_shape = tf.pack([tf.shape(h_relu4)[0], IMAGE_SIZE, IMAGE_SIZE, NUM_OF_CHANNELS])
h_conv_t5 = utils.conv2d_transpose_strided(h_relu4, W_5, b_5, output_shape=deconv_shape)
pred_image = tf.nn.tanh(h_conv_t5, name='pred_image')
utils.add_activation_summary(pred_image)
return pred_image
def generator(z, train_mode):
with tf.variable_scope("generator") as scope:
W_0 = utils.weight_variable([FLAGS.z_dim, 64 * GEN_DIMENSION / 2 * IMAGE_SIZE / 16 * IMAGE_SIZE / 16],
name="W_0")
b_0 = utils.bias_variable([64 * GEN_DIMENSION / 2 * IMAGE_SIZE / 16 * IMAGE_SIZE / 16], name="b_0")
z_0 = tf.matmul(z, W_0) + b_0
h_0 = tf.reshape(z_0, [-1, IMAGE_SIZE / 16, IMAGE_SIZE / 16, 64 * GEN_DIMENSION / 2])
h_bn0 = utils.batch_norm(h_0, 64 * GEN_DIMENSION / 2, train_mode, scope="gen_bn0")
h_relu0 = tf.nn.relu(h_bn0, name='relu0')
utils.add_activation_summary(h_relu0)
# W_1 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION/2, 64 * GEN_DIMENSION], name="W_1")
# b_1 = utils.bias_variable([64 * GEN_DIMENSION/2], name="b_1")
# deconv_shape = tf.pack([tf.shape(h_relu0)[0], IMAGE_SIZE / 16, IMAGE_SIZE / 16, 64 * GEN_DIMENSION/2])
# h_conv_t1 = utils.conv2d_transpose_strided(h_relu0, W_1, b_1, output_shape=deconv_shape)
# h_bn1 = utils.batch_norm(h_conv_t1, 64 * GEN_DIMENSION/2, train_mode, scope="gen_bn1")
# h_relu1 = tf.nn.relu(h_bn1, name='relu1')
# utils.add_activation_summary(h_relu1)
W_2 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION / 4, 64 * GEN_DIMENSION / 2],
name="W_2")
b_2 = utils.bias_variable([64 * GEN_DIMENSION / 4], name="b_2")
deconv_shape = tf.pack([tf.shape(h_relu0)[0], IMAGE_SIZE / 8, IMAGE_SIZE / 8, 64 * GEN_DIMENSION / 4])
h_conv_t2 = utils.conv2d_transpose_strided(h_relu0, W_2, b_2, output_shape=deconv_shape)
h_bn2 = utils.batch_norm(h_conv_t2, 64 * GEN_DIMENSION / 4, train_mode, scope="gen_bn2")
h_relu2 = tf.nn.relu(h_bn2, name='relu2')
utils.add_activation_summary(h_relu2)
W_3 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION / 8, 64 * GEN_DIMENSION / 4],
name="W_3")
b_3 = utils.bias_variable([64 * GEN_DIMENSION / 8], name="b_3")
deconv_shape = tf.pack([tf.shape(h_relu2)[0], IMAGE_SIZE / 4, IMAGE_SIZE / 4, 64 * GEN_DIMENSION / 8])
h_conv_t3 = utils.conv2d_transpose_strided(h_relu2, W_3, b_3, output_shape=deconv_shape)
h_bn3 = utils.batch_norm(h_conv_t3, 64 * GEN_DIMENSION / 8, train_mode, scope="gen_bn3")
h_relu3 = tf.nn.relu(h_bn3, name='relu3')
utils.add_activation_summary(h_relu3)
W_4 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION / 16, 64 * GEN_DIMENSION / 8],
name="W_4")
b_4 = utils.bias_variable([64 * GEN_DIMENSION / 16], name="b_4")
deconv_shape = tf.pack([tf.shape(h_relu3)[0], IMAGE_SIZE / 2, IMAGE_SIZE / 2, 64 * GEN_DIMENSION / 16])
h_conv_t4 = utils.conv2d_transpose_strided(h_relu3, W_4, b_4, output_shape=deconv_shape)
h_bn4 = utils.batch_norm(h_conv_t4, 64 * GEN_DIMENSION / 16, train_mode, scope="gen_bn4")
h_relu4 = tf.nn.relu(h_bn4, name='relu4')
utils.add_activation_summary(h_relu4)
W_5 = utils.weight_variable([5, 5, NUM_OF_CHANNELS, 64 * GEN_DIMENSION / 16], name="W_5")
b_5 = utils.bias_variable([NUM_OF_CHANNELS], name="b_5")
deconv_shape = tf.pack([tf.shape(h_relu4)[0], IMAGE_SIZE, IMAGE_SIZE, NUM_OF_CHANNELS])
h_conv_t5 = utils.conv2d_transpose_strided(h_relu4, W_5, b_5, output_shape=deconv_shape)
pred_image = tf.nn.tanh(h_conv_t5, name='pred_image')
utils.add_activation_summary(pred_image)
return pred_image
def vgg_net(weights, image, is_train):
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]
# matconvnet: weights are [width, height, in_channels, out_channels]
# tensorflow: weights are [height, width, in_channels, out_channels]
kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)),
name='%s_w' % name)
current = utils.conv2d_basic(current, kernels, None)
current = utils.batch_norm(current,
kernels.get_shape()[3], is_train,
'%s_bn' % name)
elif kind == 'relu':
current = tf.nn.relu(current, name='%s' % name)
if FLAGS.debug:
utils.add_activation_summary(current)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net
def encoder(dataset, train_mode):
with tf.variable_scope("Encoder"):
with tf.name_scope("enc_conv1") as scope:
W_conv1 = utils.weight_variable_xavier_initialized([3, 3, 3, 32], name="W_conv1")
b_conv1 = utils.bias_variable([32], name="b_conv1")
h_conv1 = utils.conv2d_strided(dataset, W_conv1, b_conv1)
h_bn1 = utils.batch_norm(h_conv1, 32, train_mode, scope="conv1_bn")
h_relu1 = tf.nn.relu(h_bn1)
with tf.name_scope("enc_conv2") as scope:
W_conv2 = utils.weight_variable_xavier_initialized([3, 3, 32, 64], name="W_conv2")
b_conv2 = utils.bias_variable([64], name="b_conv2")
h_conv2 = utils.conv2d_strided(h_relu1, W_conv2, b_conv2)
h_bn2 = utils.batch_norm(h_conv2, 64, train_mode, scope="conv2_bn")
h_relu2 = tf.nn.relu(h_bn2)
with tf.name_scope("enc_conv3") as scope:
W_conv3 = utils.weight_variable_xavier_initialized([3, 3, 64, 128], name="W_conv3")
b_conv3 = utils.bias_variable([128], name="b_conv3")
h_conv3 = utils.conv2d_strided(h_relu2, W_conv3, b_conv3)
h_bn3 = utils.batch_norm(h_conv3, 128, train_mode, scope="conv3_bn")
h_relu3 = tf.nn.relu(h_bn3)
with tf.name_scope("enc_conv4") as scope:
W_conv4 = utils.weight_variable_xavier_initialized([3, 3, 128, 256], name="W_conv4")
b_conv4 = utils.bias_variable([256], name="b_conv4")
h_conv4 = utils.conv2d_strided(h_relu3, W_conv4, b_conv4)
h_bn4 = utils.batch_norm(h_conv4, 256, train_mode, scope="conv4_bn")
h_relu4 = tf.nn.relu(h_bn4)
with tf.name_scope("enc_conv5") as scope:
W_conv5 = utils.weight_variable_xavier_initialized([3, 3, 256, 512], name="W_conv5")
b_conv5 = utils.bias_variable([512], name="b_conv5")
h_conv5 = utils.conv2d_strided(h_relu4, W_conv5, b_conv5)
h_bn5 = utils.batch_norm(h_conv5, 512, train_mode, scope="conv5_bn")
h_relu5 = tf.nn.relu(h_bn5)
with tf.name_scope("enc_fc") as scope:
image_size = IMAGE_SIZE // 32
h_relu5_flatten = tf.reshape(h_relu5, [-1, image_size * image_size * 512])
W_fc = utils.weight_variable([image_size * image_size * 512, 1024], name="W_fc")
b_fc = utils.bias_variable([1024], name="b_fc")
encoder_val = tf.matmul(h_relu5_flatten, W_fc) + b_fc
return encoder_val
def discriminator(input_images, train_mode):
# dropout_prob = 1.0
# if train_mode:
# dropout_prob = 0.5
W_conv0 = utils.weight_variable([5, 5, NUM_OF_CHANNELS, 64 * 1],
name="W_conv0")
b_conv0 = utils.bias_variable([64 * 1], name="b_conv0")
h_conv0 = utils.conv2d_strided(input_images, W_conv0, b_conv0)
h_bn0 = h_conv0 # utils.batch_norm(h_conv0, 64 * 1, train_mode, scope="disc_bn0")
h_relu0 = utils.leaky_relu(h_bn0, 0.2, name="h_relu0")
utils.add_activation_summary(h_relu0)
W_conv1 = utils.weight_variable([5, 5, 64 * 1, 64 * 2], name="W_conv1")
b_conv1 = utils.bias_variable([64 * 2], name="b_conv1")
h_conv1 = utils.conv2d_strided(h_relu0, W_conv1, b_conv1)
h_bn1 = utils.batch_norm(h_conv1, 64 * 2, train_mode, scope="disc_bn1")
h_relu1 = utils.leaky_relu(h_bn1, 0.2, name="h_relu1")
utils.add_activation_summary(h_relu1)
W_conv2 = utils.weight_variable([5, 5, 64 * 2, 64 * 4], name="W_conv2")
b_conv2 = utils.bias_variable([64 * 4], name="b_conv2")
h_conv2 = utils.conv2d_strided(h_relu1, W_conv2, b_conv2)
h_bn2 = utils.batch_norm(h_conv2, 64 * 4, train_mode, scope="disc_bn2")
h_relu2 = utils.leaky_relu(h_bn2, 0.2, name="h_relu2")
utils.add_activation_summary(h_relu2)
W_conv3 = utils.weight_variable([5, 5, 64 * 4, 64 * 8], name="W_conv3")
b_conv3 = utils.bias_variable([64 * 8], name="b_conv3")
h_conv3 = utils.conv2d_strided(h_relu2, W_conv3, b_conv3)
h_bn3 = utils.batch_norm(h_conv3, 64 * 8, train_mode, scope="disc_bn3")
h_relu3 = utils.leaky_relu(h_bn3, 0.2, name="h_relu3")
utils.add_activation_summary(h_relu3)
shape = h_relu3.get_shape().as_list()
h_3 = tf.reshape(
h_relu3,
[FLAGS.batch_size, (IMAGE_SIZE // 16) * (IMAGE_SIZE // 16) * shape[3]])
W_4 = utils.weight_variable([h_3.get_shape().as_list()[1], 1], name="W_4")
b_4 = utils.bias_variable([1], name="b_4")
h_4 = tf.matmul(h_3, W_4) + b_4
return tf.nn.sigmoid(h_4), h_4, h_relu3
def inpainter(embedding, train_mode):
with tf.variable_scope("context_inpainter"):
image_size = IMAGE_SIZE // 32
with tf.name_scope("dec_fc") as scope:
W_fc = utils.weight_variable([1024, image_size * image_size * 512], name="W_fc")
b_fc = utils.bias_variable([image_size * image_size * 512], name="b_fc")
h_fc = tf.nn.relu(tf.matmul(embedding, W_fc) + b_fc)
with tf.name_scope("dec_conv1") as scope:
h_reshaped = tf.reshape(h_fc, tf.pack([tf.shape(h_fc)[0], image_size, image_size, 512]))
W_conv_t1 = utils.weight_variable_xavier_initialized([3, 3, 256, 512], name="W_conv_t1")
b_conv_t1 = utils.bias_variable([256], name="b_conv_t1")
deconv_shape = tf.pack([tf.shape(h_reshaped)[0], 2 * image_size, 2 * image_size, 256])
h_conv_t1 = utils.conv2d_transpose_strided(h_reshaped, W_conv_t1, b_conv_t1, output_shape=deconv_shape)
h_bn_t1 = utils.batch_norm(h_conv_t1, 256, train_mode, scope="conv_t1_bn")
h_relu_t1 = tf.nn.relu(h_bn_t1)
with tf.name_scope("dec_conv2") as scope:
W_conv_t2 = utils.weight_variable_xavier_initialized([3, 3, 128, 256], name="W_conv_t2")
b_conv_t2 = utils.bias_variable([128], name="b_conv_t2")
deconv_shape = tf.pack([tf.shape(h_relu_t1)[0], 4 * image_size, 4 * image_size, 128])
h_conv_t2 = utils.conv2d_transpose_strided(h_relu_t1, W_conv_t2, b_conv_t2, output_shape=deconv_shape)
h_bn_t2 = utils.batch_norm(h_conv_t2, 128, train_mode, scope="conv_t2_bn")
h_relu_t2 = tf.nn.relu(h_bn_t2)
with tf.name_scope("dec_conv3") as scope:
W_conv_t3 = utils.weight_variable_xavier_initialized([3, 3, 64, 128], name="W_conv_t3")
b_conv_t3 = utils.bias_variable([64], name="b_conv_t3")
deconv_shape = tf.pack([tf.shape(h_relu_t2)[0], 8 * image_size, 8 * image_size, 64])
h_conv_t3 = utils.conv2d_transpose_strided(h_relu_t2, W_conv_t3, b_conv_t3, output_shape=deconv_shape)
h_bn_t3 = utils.batch_norm(h_conv_t3, 64, train_mode, scope="conv_t3_bn")
h_relu_t3 = tf.nn.relu(h_bn_t3)
with tf.name_scope("dec_conv4") as scope:
W_conv_t4 = utils.weight_variable_xavier_initialized([3, 3, 3, 64], name="W_conv_t4")
b_conv_t4 = utils.bias_variable([3], name="b_conv_t4")
deconv_shape = tf.pack([tf.shape(h_relu_t3)[0], 16 * image_size, 16 * image_size, 3])
pred_image = utils.conv2d_transpose_strided(h_relu_t3, W_conv_t4, b_conv_t4, output_shape=deconv_shape)
return pred_image
def discriminator(input_images, train_mode):
# dropout_prob = 1.0
# if train_mode:
# dropout_prob = 0.5
W_conv0 = utils.weight_variable([5, 5, NUM_OF_CHANNELS, 64 * 1], name="W_conv0")
b_conv0 = utils.bias_variable([64 * 1], name="b_conv0")
h_conv0 = utils.conv2d_strided(input_images, W_conv0, b_conv0)
h_bn0 = h_conv0 # utils.batch_norm(h_conv0, 64 * 1, train_mode, scope="disc_bn0")
h_relu0 = utils.leaky_relu(h_bn0, 0.2, name="h_relu0")
utils.add_activation_summary(h_relu0)
W_conv1 = utils.weight_variable([5, 5, 64 * 1, 64 * 2], name="W_conv1")
b_conv1 = utils.bias_variable([64 * 2], name="b_conv1")
h_conv1 = utils.conv2d_strided(h_relu0, W_conv1, b_conv1)
h_bn1 = utils.batch_norm(h_conv1, 64 * 2, train_mode, scope="disc_bn1")
h_relu1 = utils.leaky_relu(h_bn1, 0.2, name="h_relu1")
utils.add_activation_summary(h_relu1)
W_conv2 = utils.weight_variable([5, 5, 64 * 2, 64 * 4], name="W_conv2")
b_conv2 = utils.bias_variable([64 * 4], name="b_conv2")
h_conv2 = utils.conv2d_strided(h_relu1, W_conv2, b_conv2)
h_bn2 = utils.batch_norm(h_conv2, 64 * 4, train_mode, scope="disc_bn2")
h_relu2 = utils.leaky_relu(h_bn2, 0.2, name="h_relu2")
utils.add_activation_summary(h_relu2)
W_conv3 = utils.weight_variable([5, 5, 64 * 4, 64 * 8], name="W_conv3")
b_conv3 = utils.bias_variable([64 * 8], name="b_conv3")
h_conv3 = utils.conv2d_strided(h_relu2, W_conv3, b_conv3)
h_bn3 = utils.batch_norm(h_conv3, 64 * 8, train_mode, scope="disc_bn3")
h_relu3 = utils.leaky_relu(h_bn3, 0.2, name="h_relu3")
utils.add_activation_summary(h_relu3)
shape = h_relu3.get_shape().as_list()
h_3 = tf.reshape(h_relu3, [FLAGS.batch_size, (IMAGE_SIZE // 16) * (IMAGE_SIZE // 16) * shape[3]])
W_4 = utils.weight_variable([h_3.get_shape().as_list()[1], 1], name="W_4")
b_4 = utils.bias_variable([1], name="b_4")
h_4 = tf.matmul(h_3, W_4) + b_4
return tf.nn.sigmoid(h_4), h_4, h_relu3
def u_net(image, phase_train):
with tf.variable_scope("u_net"):
w1_1 = utils.weight_variable([3, 3, int(image.shape[3]), 32],
name="w1_1")
b1_1 = utils.bias_variable([32], name="b1_1")
conv1_1 = utils.conv2d_basic(image, w1_1, b1_1)
relu1_1 = tf.nn.relu(conv1_1, name="relu1_1")
w1_2 = utils.weight_variable([3, 3, 32, 32], name="w1_2")
b1_2 = utils.bias_variable([32], name="b1_2")
conv1_2 = utils.conv2d_basic(relu1_1, w1_2, b1_2)
relu1_2 = tf.nn.relu(conv1_2, name="relu1_2")
pool1 = utils.max_pool_2x2(relu1_2)
bn1 = utils.batch_norm(pool1,
pool1.get_shape()[3],
phase_train,
scope="bn1")
w2_1 = utils.weight_variable([3, 3, 32, 64], name="w2_1")
b2_1 = utils.bias_variable([64], name="b2_1")
conv2_1 = utils.conv2d_basic(bn1, w2_1, b2_1)
relu2_1 = tf.nn.relu(conv2_1, name="relu2_1")
w2_2 = utils.weight_variable([3, 3, 64, 64], name="w2_2")
b2_2 = utils.bias_variable([64], name="b2_2")
conv2_2 = utils.conv2d_basic(relu2_1, w2_2, b2_2)
relu2_2 = tf.nn.relu(conv2_2, name="relu2_2")
pool2 = utils.max_pool_2x2(relu2_2)
bn2 = utils.batch_norm(pool2,
pool2.get_shape()[3],
phase_train,
scope="bn2")
w3_1 = utils.weight_variable([3, 3, 64, 128], name="w3_1")
b3_1 = utils.bias_variable([128], name="b3_1")
conv3_1 = utils.conv2d_basic(bn2, w3_1, b3_1)
relu3_1 = tf.nn.relu(conv3_1, name="relu3_1")
w3_2 = utils.weight_variable([3, 3, 128, 128], name="w3_2")
b3_2 = utils.bias_variable([128], name="b3_2")
conv3_2 = utils.conv2d_basic(relu3_1, w3_2, b3_2)
relu3_2 = tf.nn.relu(conv3_2, name="relu3_2")
pool3 = utils.max_pool_2x2(relu3_2)
bn3 = utils.batch_norm(pool3,
pool3.get_shape()[3],
phase_train,
scope="bn3")
w4_1 = utils.weight_variable([3, 3, 128, 256], name="w4_1")
b4_1 = utils.bias_variable([256], name="b4_1")
conv4_1 = utils.conv2d_basic(bn3, w4_1, b4_1)
relu4_1 = tf.nn.relu(conv4_1, name="relu4_1")
w4_2 = utils.weight_variable([3, 3, 256, 256], name="w4_2")
b4_2 = utils.bias_variable([256], name="b4_2")
conv4_2 = utils.conv2d_basic(relu4_1, w4_2, b4_2)
relu4_2 = tf.nn.relu(conv4_2, name="relu4_2")
pool4 = utils.max_pool_2x2(relu4_2)
bn4 = utils.batch_norm(pool4,
pool4.get_shape()[3],
phase_train,
scope="bn4")
w5_1 = utils.weight_variable([3, 3, 256, 512], name="w5_1")
b5_1 = utils.bias_variable([512], name="b5_1")
conv5_1 = utils.conv2d_basic(bn4, w5_1, b5_1)
relu5_1 = tf.nn.relu(conv5_1, name="relu5_1")
w5_2 = utils.weight_variable([3, 3, 512, 512], name="w5_2")
b5_2 = utils.bias_variable([512], name="b5_2")
conv5_2 = utils.conv2d_basic(relu5_1, w5_2, b5_2)
relu5_2 = tf.nn.relu(conv5_2, name="relu5_2")
bn5 = utils.batch_norm(relu5_2,
relu5_2.get_shape()[3],
phase_train,
scope="bn5")
###up6
W_t1 = utils.weight_variable([2, 2, 256, 512], name="W_t1")
b_t1 = utils.bias_variable([256], name="b_t1")
conv_t1 = utils.conv2d_transpose_strided(
bn5, W_t1, b_t1, output_shape=tf.shape(relu4_2))
merge1 = tf.concat([conv_t1, relu4_2], 3)
w6_1 = utils.weight_variable([3, 3, 512, 256], name="w6_1")
b6_1 = utils.bias_variable([256], name="b6_1")
conv6_1 = utils.conv2d_basic(merge1, w6_1, b6_1)
relu6_1 = tf.nn.relu(conv6_1, name="relu6_1")
w6_2 = utils.weight_variable([3, 3, 256, 256], name="w6_2")
b6_2 = utils.bias_variable([256], name="b6_2")
conv6_2 = utils.conv2d_basic(relu6_1, w6_2, b6_2)
relu6_2 = tf.nn.relu(conv6_2, name="relu6_2")
bn6 = utils.batch_norm(relu6_2,
relu6_2.get_shape()[3],
phase_train,
scope="bn6")
###up7
W_t2 = utils.weight_variable([2, 2, 128, 256], name="W_t2")
b_t2 = utils.bias_variable([128], name="b_t2")
conv_t2 = utils.conv2d_transpose_strided(
bn6, W_t2, b_t2, output_shape=tf.shape(relu3_2))
merge2 = tf.concat([conv_t2, relu3_2], 3)
w7_1 = utils.weight_variable([3, 3, 256, 128], name="w7_1")
b7_1 = utils.bias_variable([128], name="b7_1")
conv7_1 = utils.conv2d_basic(merge2, w7_1, b7_1)
relu7_1 = tf.nn.relu(conv7_1, name="relu7_1")
w7_2 = utils.weight_variable([3, 3, 128, 128], name="w7_2")
b7_2 = utils.bias_variable([128], name="b7_2")
conv7_2 = utils.conv2d_basic(relu7_1, w7_2, b7_2)
relu7_2 = tf.nn.relu(conv7_2, name="relu7_2")
bn7 = utils.batch_norm(relu7_2,
relu7_2.get_shape()[3],
phase_train,
scope="bn7")
###up8
W_t3 = utils.weight_variable([2, 2, 64, 128], name="W_t3")
b_t3 = utils.bias_variable([64], name="b_t3")
conv_t3 = utils.conv2d_transpose_strided(
bn7, W_t3, b_t3, output_shape=tf.shape(relu2_2))
merge3 = tf.concat([conv_t3, relu2_2], 3)
w8_1 = utils.weight_variable([3, 3, 128, 64], name="w8_1")
b8_1 = utils.bias_variable([64], name="b8_1")
conv8_1 = utils.conv2d_basic(merge3, w8_1, b8_1)
relu8_1 = tf.nn.relu(conv8_1, name="relu8_1")
w8_2 = utils.weight_variable([3, 3, 64, 64], name="w8_2")
b8_2 = utils.bias_variable([64], name="b8_2")
conv8_2 = utils.conv2d_basic(relu8_1, w8_2, b8_2)
relu8_2 = tf.nn.relu(conv8_2, name="relu8_2")
bn8 = utils.batch_norm(relu8_2,
relu8_2.get_shape()[3],
phase_train,
scope="bn8")
###up9
W_t4 = utils.weight_variable([2, 2, 32, 64], name="W_t4")
b_t4 = utils.bias_variable([32], name="b_t4")
conv_t4 = utils.conv2d_transpose_strided(
bn8, W_t4, b_t4, output_shape=tf.shape(relu1_2))
merge4 = tf.concat([conv_t4, relu1_2], 3)
w9_1 = utils.weight_variable([3, 3, 64, 32], name="w9_1")
b9_1 = utils.bias_variable([32], name="b9_1")
conv9_1 = utils.conv2d_basic(merge4, w9_1, b9_1)
relu9_1 = tf.nn.relu(conv9_1, name="relu9_1")
w9_2 = utils.weight_variable([3, 3, 32, 32], name="w9_2")
b9_2 = utils.bias_variable([32], name="b9_2")
conv9_2 = utils.conv2d_basic(relu9_1, w9_2, b9_2)
relu9_2 = tf.nn.relu(conv9_2, name="relu9_2")
bn9 = utils.batch_norm(relu9_2,
relu9_2.get_shape()[3],
phase_train,
scope="bn9")
###output scoreMap
w10 = utils.weight_variable([1, 1, 32, NUM_OF_CLASSESS], name="w10")
b10 = utils.bias_variable([NUM_OF_CLASSESS], name="b10")
conv10 = utils.conv2d_basic(bn9, w10, b10)
annotation_pred = tf.argmax(conv10, dimension=3, name="prediction")
return annotation_pred, conv10
def inpainter(embedding, train_mode):
with tf.variable_scope("context_inpainter"):
image_size = IMAGE_SIZE // 32
with tf.name_scope("dec_fc") as scope:
W_fc = utils.weight_variable([1024, image_size * image_size * 512],
name="W_fc")
b_fc = utils.bias_variable([image_size * image_size * 512],
name="b_fc")
h_fc = tf.nn.relu(tf.matmul(embedding, W_fc) + b_fc)
with tf.name_scope("dec_conv1") as scope:
h_reshaped = tf.reshape(
h_fc, tf.pack([tf.shape(h_fc)[0], image_size, image_size,
512]))
W_conv_t1 = utils.weight_variable_xavier_initialized(
[3, 3, 256, 512], name="W_conv_t1")
b_conv_t1 = utils.bias_variable([256], name="b_conv_t1")
deconv_shape = tf.pack(
[tf.shape(h_reshaped)[0], 2 * image_size, 2 * image_size, 256])
h_conv_t1 = utils.conv2d_transpose_strided(
h_reshaped, W_conv_t1, b_conv_t1, output_shape=deconv_shape)
h_bn_t1 = utils.batch_norm(h_conv_t1,
256,
train_mode,
scope="conv_t1_bn")
h_relu_t1 = tf.nn.relu(h_bn_t1)
with tf.name_scope("dec_conv2") as scope:
W_conv_t2 = utils.weight_variable_xavier_initialized(
[3, 3, 128, 256], name="W_conv_t2")
b_conv_t2 = utils.bias_variable([128], name="b_conv_t2")
deconv_shape = tf.pack(
[tf.shape(h_relu_t1)[0], 4 * image_size, 4 * image_size, 128])
h_conv_t2 = utils.conv2d_transpose_strided(
h_relu_t1, W_conv_t2, b_conv_t2, output_shape=deconv_shape)
h_bn_t2 = utils.batch_norm(h_conv_t2,
128,
train_mode,
scope="conv_t2_bn")
h_relu_t2 = tf.nn.relu(h_bn_t2)
with tf.name_scope("dec_conv3") as scope:
W_conv_t3 = utils.weight_variable_xavier_initialized(
[3, 3, 64, 128], name="W_conv_t3")
b_conv_t3 = utils.bias_variable([64], name="b_conv_t3")
deconv_shape = tf.pack(
[tf.shape(h_relu_t2)[0], 8 * image_size, 8 * image_size, 64])
h_conv_t3 = utils.conv2d_transpose_strided(
h_relu_t2, W_conv_t3, b_conv_t3, output_shape=deconv_shape)
h_bn_t3 = utils.batch_norm(h_conv_t3,
64,
train_mode,
scope="conv_t3_bn")
h_relu_t3 = tf.nn.relu(h_bn_t3)
with tf.name_scope("dec_conv4") as scope:
W_conv_t4 = utils.weight_variable_xavier_initialized(
[3, 3, 3, 64], name="W_conv_t4")
b_conv_t4 = utils.bias_variable([3], name="b_conv_t4")
deconv_shape = tf.pack(
[tf.shape(h_relu_t3)[0], 16 * image_size, 16 * image_size, 3])
pred_image = utils.conv2d_transpose_strided(
h_relu_t3, W_conv_t4, b_conv_t4, output_shape=deconv_shape)
return pred_image
def encoder(dataset, train_mode):
with tf.variable_scope("Encoder"):
with tf.name_scope("enc_conv1") as scope:
W_conv1 = utils.weight_variable_xavier_initialized([3, 3, 3, 32],
name="W_conv1")
b_conv1 = utils.bias_variable([32], name="b_conv1")
h_conv1 = utils.conv2d_strided(dataset, W_conv1, b_conv1)
h_bn1 = utils.batch_norm(h_conv1, 32, train_mode, scope="conv1_bn")
h_relu1 = tf.nn.relu(h_bn1)
with tf.name_scope("enc_conv2") as scope:
W_conv2 = utils.weight_variable_xavier_initialized([3, 3, 32, 64],
name="W_conv2")
b_conv2 = utils.bias_variable([64], name="b_conv2")
h_conv2 = utils.conv2d_strided(h_relu1, W_conv2, b_conv2)
h_bn2 = utils.batch_norm(h_conv2, 64, train_mode, scope="conv2_bn")
h_relu2 = tf.nn.relu(h_bn2)
with tf.name_scope("enc_conv3") as scope:
W_conv3 = utils.weight_variable_xavier_initialized([3, 3, 64, 128],
name="W_conv3")
b_conv3 = utils.bias_variable([128], name="b_conv3")
h_conv3 = utils.conv2d_strided(h_relu2, W_conv3, b_conv3)
h_bn3 = utils.batch_norm(h_conv3,
128,
train_mode,
scope="conv3_bn")
h_relu3 = tf.nn.relu(h_bn3)
with tf.name_scope("enc_conv4") as scope:
W_conv4 = utils.weight_variable_xavier_initialized(
[3, 3, 128, 256], name="W_conv4")
b_conv4 = utils.bias_variable([256], name="b_conv4")
h_conv4 = utils.conv2d_strided(h_relu3, W_conv4, b_conv4)
h_bn4 = utils.batch_norm(h_conv4,
256,
train_mode,
scope="conv4_bn")
h_relu4 = tf.nn.relu(h_bn4)
with tf.name_scope("enc_conv5") as scope:
W_conv5 = utils.weight_variable_xavier_initialized(
[3, 3, 256, 512], name="W_conv5")
b_conv5 = utils.bias_variable([512], name="b_conv5")
h_conv5 = utils.conv2d_strided(h_relu4, W_conv5, b_conv5)
h_bn5 = utils.batch_norm(h_conv5,
512,
train_mode,
scope="conv5_bn")
h_relu5 = tf.nn.relu(h_bn5)
with tf.name_scope("enc_fc") as scope:
image_size = IMAGE_SIZE // 32
h_relu5_flatten = tf.reshape(h_relu5,
[-1, image_size * image_size * 512])
W_fc = utils.weight_variable([image_size * image_size * 512, 1024],
name="W_fc")
b_fc = utils.bias_variable([1024], name="b_fc")
encoder_val = tf.matmul(h_relu5_flatten, W_fc) + b_fc
return encoder_val
