def inference_conv(dataset):
dataset_reshaped = tf.reshape(dataset, [-1, 28, 28, 1])
with tf.name_scope("conv1") as scope:
W_conv1 = utils.weight_variable([5, 5, 1, 32], name="W_conv1")
bias1 = utils.bias_variable([32], name="bias1")
tf.histogram_summary("W_conv1", W_conv1)
tf.histogram_summary("bias1", bias1)
h_conv1 = tf.nn.relu(
utils.conv2d_basic(dataset_reshaped, W_conv1, bias1))
h_norm1 = utils.local_response_norm(h_conv1)
h_pool1 = utils.max_pool_2x2(h_norm1)
with tf.name_scope("conv2") as scope:
W_conv2 = utils.weight_variable([3, 3, 32, 64], name="W_conv2")
bias2 = utils.bias_variable([64], name="bias2")
tf.histogram_summary("W_conv2", W_conv2)
tf.histogram_summary("bias2", bias2)
h_conv2 = tf.nn.relu(utils.conv2d_basic(h_pool1, W_conv2, bias2))
h_norm2 = utils.local_response_norm(h_conv2)
h_pool2 = utils.max_pool_2x2(h_norm2)
with tf.name_scope("fc1") as scope:
h_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
W_fc1 = utils.weight_variable([7 * 7 * 64, 10], name="W_fc1")
bias_fc1 = utils.bias_variable([10], name="bias_fc1")
tf.histogram_summary("W_fc1", W_fc1)
tf.histogram_summary("bias_fc1", bias_fc1)
logits = tf.matmul(h_flat, W_fc1) + bias_fc1
return logits
def inference_simple(dataset):
with tf.name_scope("conv1") as scope:
W1 = utils.weight_variable([5, 5, 1, 32], name="W1")
b1 = utils.bias_variable([32], name="b1")
tf.histogram_summary("W1", W1)
tf.histogram_summary("b1", b1)
h_conv1 = tf.nn.relu(utils.conv2d_basic(dataset, W1, b1), name="h_conv1")
h_pool1 = utils.max_pool_2x2(h_conv1)
with tf.name_scope("conv2") as scope:
W2 = utils.weight_variable([3, 3, 32, 64], name="W2")
b2 = utils.bias_variable([64], name="b2")
tf.histogram_summary("W2", W2)
tf.histogram_summary("b2", b2)
h_conv2 = tf.nn.relu(utils.conv2d_basic(h_pool1, W2, b2), name="h_conv2")
h_pool2 = utils.max_pool_2x2(h_conv2)
with tf.name_scope("fc") as scope:
image_size = IMAGE_SIZE // 4
h_flat = tf.reshape(h_pool2, [-1, image_size * image_size * 64])
W_fc = utils.weight_variable([image_size * image_size * 64, NUM_LABELS], name="W_fc")
b_fc = utils.bias_variable([NUM_LABELS], name="b_fc")
tf.histogram_summary("W_fc", W_fc)
tf.histogram_summary("b_fc", b_fc)
pred = tf.matmul(h_flat, W_fc) + b_fc
return pred
def inference(image, keep_prob):
print("setting up vgg initialized conv layers ...")
model_data = utils.get_model_data(FLAGS.model_dir, MODEL_URL)
mean = model_data['normalization'][0][0][0]
mean_pixel = np.mean(mean, axis=(0, 1))
weights = np.squeeze(model_data['layers'])
processed_image = utils.process_image(image, mean_pixel)
with tf.variable_scope("inference"):
image_net = vgg_net(weights, processed_image)
conv_final_layer = image_net["conv5_3"]
pool5 = utils.max_pool_2x2(conv_final_layer)
W6 = utils.weight_variable([7, 7, 512, 4096], name="W6")
b6 = utils.bias_variable([4096], name="b6")
conv6 = utils.conv2d_basic(pool5, W6, b6)
relu6 = tf.nn.relu(conv6, name="relu6")
if FLAGS.debug:
utils.add_activation_summary(relu6)
relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob)
W7 = utils.weight_variable([1, 1, 4096, 4096], name="W7")
b7 = utils.bias_variable([4096], name="b7")
conv7 = utils.conv2d_basic(relu_dropout6, W7, b7)
relu7 = tf.nn.relu(conv7, name="relu7")
if FLAGS.debug:
utils.add_activation_summary(relu7)
relu_dropout7 = tf.nn.dropout(relu7, keep_prob=keep_prob)
W8 = utils.weight_variable([1, 1, 4096, NUM_OF_CLASSESS], name="W8")
b8 = utils.bias_variable([NUM_OF_CLASSESS], name="b8")
conv8 = utils.conv2d_basic(relu_dropout7, W8, b8)
deconv_shape1 = image_net["pool4"].get_shape()
W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, NUM_OF_CLASSESS], name="W_t1")
b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1")
conv_t1 = utils.conv2d_transpose_strided(conv8, W_t1, b_t1, output_shape=tf.shape(image_net["pool4"]))
fuse_1 = tf.add(conv_t1, image_net["pool4"], name="fuse_1")
deconv_shape2 = image_net["pool3"].get_shape()
W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, deconv_shape1[3].value], name="W_t2")
b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
conv_t2 = utils.conv2d_transpose_strided(fuse_1, W_t2, b_t2, output_shape=tf.shape(image_net["pool3"]))
fuse_2 = tf.add(conv_t2, image_net["pool3"], name="fuse_2")
shape = tf.shape(image)
deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], NUM_OF_CLASSESS])
W_t3 = utils.weight_variable([16, 16, NUM_OF_CLASSESS, deconv_shape2[3].value], name="W_t3")
b_t3 = utils.bias_variable([NUM_OF_CLASSESS], name="b_t3")
conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=deconv_shape3, stride=8)
annotation_pred = tf.argmax(conv_t3, dimension=3, name="prediction")
return tf.expand_dims(annotation_pred, dim=3), conv_t3
def deepscores_cnn(image, nr_class):
# placeholder for dropout input
keep_prob = tf.placeholder(tf.float32)
# five layers of 3x3 convolutions, followed by relu, 2x2-maxpool and dropout
W1 = utils.weight_variable([3, 3, 1, 32], name="W1")
b1 = utils.bias_variable([32], name="b1")
conv1 = utils.conv2d_basic(image, W1, b1, name="conv1")
relu1 = tf.nn.relu(conv1, name="relu1")
pool1 = utils.max_pool_2x2(relu1)
dropout1 = tf.nn.dropout(pool1, keep_prob=keep_prob)
W2 = utils.weight_variable([3, 3, 32, 64], name="W2")
b2 = utils.bias_variable([64], name="b2")
conv2 = utils.conv2d_basic(dropout1, W2, b2, name="conv2")
relu2 = tf.nn.relu(conv2, name="relu2")
pool2 = utils.max_pool_2x2(relu2)
dropout2 = tf.nn.dropout(pool2, keep_prob=keep_prob)
W3 = utils.weight_variable([3, 3, 64, 128], name="W3")
b3 = utils.bias_variable([128], name="b3")
conv3 = utils.conv2d_basic(dropout2, W3, b3, name="conv3")
relu3 = tf.nn.relu(conv3, name="relu3")
pool3 = utils.max_pool_2x2(relu3)
dropout3 = tf.nn.dropout(pool3, keep_prob=keep_prob)
W4 = utils.weight_variable([3, 3, 128, 256], name="W4")
b4 = utils.bias_variable([256], name="b4")
conv4 = utils.conv2d_basic(dropout3, W4, b4, name="conv4")
relu4 = tf.nn.relu(conv4, name="relu4")
pool4 = utils.max_pool_2x2(relu4)
dropout4 = tf.nn.dropout(pool4, keep_prob=keep_prob)
W5 = utils.weight_variable([3, 3, 256, 512], name="W5")
b5 = utils.bias_variable([512], name="b5")
conv5 = utils.conv2d_basic(dropout4, W5, b5, name="conv5")
relu5 = tf.nn.relu(conv5, name="relu5")
pool5 = utils.max_pool_2x2(relu5)
dropout5 = tf.nn.dropout(pool5, keep_prob=keep_prob)
# to fully connected layers
# downsampled 5 times so feature maps should be 32 times smaller
# size is 7*4*512
W_fc1 = utils.weight_variable([7*4*512, 1024])
b_fc1 = utils.bias_variable([1024])
dropout5_flat = tf.reshape(dropout5, [-1, 7*4*512])
h_fc1 = tf.nn.relu(tf.matmul(dropout5_flat, W_fc1) + b_fc1)
W_fc2 = utils.weight_variable([1024, nr_class])
b_fc2 = utils.bias_variable([nr_class])
y_conv = tf.matmul(h_fc1, W_fc2) + b_fc2
return y_conv, keep_prob
def inference(dataset):
with tf.name_scope("conv1") as scope:
W1 = utils.weight_variable([5, 5, 1, 32], name="W1")
b1 = utils.bias_variable([32], name="b1")
tf.histogram_summary("W1", W1)
tf.histogram_summary("b1", b1)
h_conv1 = utils.conv2d_basic(dataset, W1, b1)
h_norm1 = utils.local_response_norm(h_conv1)
h_1 = tf.nn.relu(h_norm1, name="conv1")
h_pool1 = utils.max_pool_2x2(h_1)
with tf.name_scope("conv2") as scope:
W2 = utils.weight_variable([3, 3, 32, 64], name="W2")
b2 = utils.bias_variable([64], name="b2")
tf.histogram_summary("W2", W2)
tf.histogram_summary("b2", b2)
h_conv2 = utils.conv2d_basic(h_pool1, W2, b2)
h_norm2 = utils.local_response_norm(h_conv2)
h_2 = tf.nn.relu(h_norm2, name="conv2")
h_pool2 = utils.max_pool_2x2(h_2)
with tf.name_scope("conv3") as scope:
W3 = utils.weight_variable([3, 3, 64, 128], name="W3")
b3 = utils.bias_variable([128], name="b3")
tf.histogram_summary("W3", W3)
tf.histogram_summary("b3", b3)
h_conv3 = utils.conv2d_basic(h_pool2, W3, b3)
h_norm3 = utils.local_response_norm(h_conv3)
h_3 = tf.nn.relu(h_norm3, name="conv3")
h_pool3 = utils.max_pool_2x2(h_3)
with tf.name_scope("conv4") as scope:
W4 = utils.weight_variable([3, 3, 128, 256], name="W4")
b4 = utils.bias_variable([256], name="b4")
tf.histogram_summary("W4", W4)
tf.histogram_summary("b4", b4)
h_conv4 = utils.conv2d_basic(h_pool3, W4, b4)
h_norm4 = utils.local_response_norm(h_conv4)
h_4 = tf.nn.relu(h_norm4, name="conv4")
with tf.name_scope("fc1") as scope:
image_size = IMAGE_SIZE // 8
h_flat = tf.reshape(h_4, [-1, image_size * image_size * 256])
W_fc1 = utils.weight_variable([image_size * image_size * 256, 512], name="W_fc1")
b_fc1 = utils.bias_variable([512], name="b_fc1")
tf.histogram_summary("W_fc1", W_fc1)
tf.histogram_summary("b_fc1", b_fc1)
h_fc1 = tf.nn.relu(tf.matmul(h_flat, W_fc1) + b_fc1)
with tf.name_scope("fc2") as scope:
W_fc2 = utils.weight_variable([512, NUM_LABELS], name="W_fc2")
b_fc2 = utils.bias_variable([NUM_LABELS], name="b_fc2")
tf.histogram_summary("W_fc2", W_fc2)
tf.histogram_summary("b_fc2", b_fc2)
pred = tf.matmul(h_fc1, W_fc2) + b_fc2
return pred
def vgg_net(weights, image):
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')
'''
weights[i][0][0][0][0]:
<tf.Variable 'inference/conv1_1_w:0' shape=(3, 3, 3, 64) dtype=float32_ref>
<tf.Variable 'inference/conv1_1_b:0' shape=(64,) dtype=float32_ref>
<tf.Variable 'inference/conv1_2_w:0' shape=(3, 3, 64, 64) dtype=float32_ref>
<tf.Variable 'inference/conv1_2_b:0' shape=(64,) dtype=float32_ref>
<tf.Variable 'inference/conv2_1_w:0' shape=(3, 3, 64, 128) dtype=float32_ref>
<tf.Variable 'inference/conv2_1_b:0' shape=(128,) dtype=float32_ref>
<tf.Variable 'inference/conv2_2_w:0' shape=(3, 3, 128, 128) dtype=float32_ref>
<tf.Variable 'inference/conv2_2_b:0' shape=(128,) dtype=float32_ref>
'''
net = {}
current = image
for i, name in enumerate(
layers
): # 对于一个可迭代/可遍历的对象（如列表、字符串），enumerate将其组成一个索引序列，利用它可以同时获得索引和值
kind = name[:4]
num = name[4:]
if kind == 'conv' and num == '1_1':
W = utils.weight_variable(
[3, 3, 4, 64],
name=name + "_w") # [patch 7*7,insize 512, outsize 4096]
b = utils.bias_variable([64], name=name + "_b")
current = utils.conv2d_basic(current, W, b)
elif kind == 'conv' and num != '1_1':
kernels, bias = weights[i][0][0][0][0]
# print("kernels:",i,kernels)
# print kernels
# 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=name + "_w")
# print(kernels)
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
# print(bias)
current = utils.conv2d_basic(current, kernels, bias)
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
if FLAGS.debug:
utils.add_activation_summary(current)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net
def fcn(inputs, keep_prob): with slim.arg_scope( [slim.conv2d, slim.fully_connected], activation_fn=tf.nn.relu, weights_initializer=tf.truncated_normal_initializer(0.0, 0.01), weights_regularizer=slim.l2_regularizer(0.0005) ): net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1') pool1 = slim.max_pool2d(net, [2, 2], scope='pool1') net = slim.repeat(pool1, 2, slim.conv2d, 128, [3, 3], scope='conv2') pool2 = slim.max_pool2d(net, [2, 2], scope='pool2') net = slim.repeat(pool2, 3, slim.conv2d, 256, [3, 3], scope='conv3') pool3 = slim.max_pool2d(net, [2, 2], scope='pool3') net = slim.repeat(pool3, 3, slim.conv2d, 512, [3, 3], scope='conv4') pool4 = slim.max_pool2d(net, [2, 2], scope='pool4') net = slim.repeat(pool4, 3, slim.conv2d, 512, [3, 3], scope='conv5') pool5 = slim.max_pool2d(net, [2, 2], scope='pool5') W6 = utils.weight_variable([7, 7, 512, 4096], name="W6") b6 = utils.bias_variable([4096], name="b6") conv6 = utils.conv2d_basic(pool5, W6, b6) relu6 = tf.nn.relu(conv6, name="relu6") relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob) W7 = utils.weight_variable([1, 1, 4096, 4096], name="W7") b7 = utils.bias_variable([4096], name="b7") conv7 = utils.conv2d_basic(relu_dropout6, W7, b7) relu7 = tf.nn.relu(conv7, name="relu7") relu_dropout7 = tf.nn.dropout(relu7, keep_prob=keep_prob) W8 = utils.weight_variable([1, 1, 4096, NUM_OF_CLASSESS], name="W8") b8 = utils.bias_variable([NUM_OF_CLASSESS], name="b8") conv8 = utils.conv2d_basic(relu_dropout7, W8, b8) # now to upscale to actual image size deconv_shape1 = pool4.get_shape() W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, NUM_OF_CLASSESS], name="W_t1") b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1") conv_t1 = utils.conv2d_transpose_strided(conv8, W_t1, b_t1, output_shape=tf.shape(pool4)) fuse_1 = tf.add(conv_t1, pool4, name="fuse_1") deconv_shape2 = pool3.get_shape() W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, deconv_shape1[3].value], name="W_t2") b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2") conv_t2 = utils.conv2d_transpose_strided(fuse_1, W_t2, b_t2, output_shape=tf.shape(pool3)) fuse_2 = tf.add(conv_t2, pool3, name="fuse_2") shape = tf.shape(inputs) deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], NUM_OF_CLASSESS]) W_t3 = utils.weight_variable([16, 16, NUM_OF_CLASSESS, deconv_shape2[3].value], name="W_t3") b_t3 = utils.bias_variable([NUM_OF_CLASSESS], name="b_t3") conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=deconv_shape3, stride=8) annotation_pred = tf.argmax(conv_t3, dimension=3, name="prediction") return tf.expand_dims(annotation_pred, dim=3), conv_t3
def inference(image, keep_prob):
"""
Semantic segmentation network definition
:param image: input image. Should have values in range 0-255
:param keep_prob:
:return:
"""
print("setting up vgg initialized conv layers ...")
model_data = utils.get_model_data(model_dir, MODEL_URL)
mean = model_data['normalization'][0][0][0]
mean_pixel = np.mean(mean, axis=(0, 1))
weights = np.squeeze(model_data['layers'])
processed_image = utils.process_image(image, mean_pixel)
with tf.variable_scope("inference"):
image_net = vgg_net(weights, processed_image)
conv_final_layer = image_net["conv4_3"]
W6 = utils.weight_variable([1, 1, 512, 1024], name="W6", init=weight_init)
b6 = utils.bias_variable([1024], name="b6")
conv6 = utils.conv2d_basic(conv_final_layer, W6, b6)
relu6 = tf.nn.relu(conv6, name="relu6")
if debug:
utils.add_activation_summary(relu6)
relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob)
W7 = utils.weight_variable([1, 1, 1024, NUM_OF_CLASSESS], name="W7", init=weight_init)
b7 = utils.bias_variable([NUM_OF_CLASSESS], name="b7")
conv7 = utils.conv2d_basic(relu_dropout6, W7, b7)
# now to upscale to actual image size
deconv_shape1 = image_net["pool2"].get_shape()
W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, NUM_OF_CLASSESS], name="W_t1", init=weight_init)
b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1")
conv_t1 = utils.conv2d_transpose_strided(conv7, W_t1, b_t1, output_shape=tf.shape(image_net["pool2"]))
fuse_1 = tf.add(conv_t1, image_net["pool2"], name="fuse_1")
deconv_shape2 = image_net["pool1"].get_shape()
W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, deconv_shape1[3].value], name="W_t2", init=weight_init)
b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
conv_t2 = utils.conv2d_transpose_strided(fuse_1, W_t2, b_t2, output_shape=tf.shape(image_net["pool1"]))
fuse_2 = tf.add(conv_t2, image_net["pool1"], name="fuse_1")
shape = tf.shape(image)
deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], NUM_OF_CLASSESS])
W_t3 = utils.weight_variable([4, 4, NUM_OF_CLASSESS, deconv_shape2[3].value], name="W_t3", init=weight_init)
b_t3 = utils.bias_variable([NUM_OF_CLASSESS], name="b_t3")
conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=deconv_shape3, stride=2)
return conv_t3
def build_centers_layers(self, image, keep_prob):
with tf.variable_scope("centers"):
pool5 = utils.max_pool_2x2(self.image_net["conv5_3"])
W6 = utils.weight_variable([7, 7, 512, 4096], name="W6")
b6 = utils.bias_variable([4096], name="b6")
conv6 = utils.conv2d_basic(pool5, W6, b6)
relu6 = tf.nn.relu(conv6, name="relu6")
if self.debug:
utils.add_activation_summary(relu6)
relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob)
W7 = utils.weight_variable([1, 1, 4096, 4096], name="W7")
b7 = utils.bias_variable([4096], name="b7")
conv7 = utils.conv2d_basic(relu_dropout6, W7, b7)
relu7 = tf.nn.relu(conv7, name="relu7")
if self.debug:
utils.add_activation_summary(relu7)
relu_dropout7 = tf.nn.dropout(relu7, keep_prob=keep_prob)
W8 = utils.weight_variable([1, 1, 4096, self.n_classes], name="W8")
b8 = utils.bias_variable([self.n_classes], name="b8")
conv8 = utils.conv2d_basic(relu_dropout7, W8, b8)
# annotation_pred1 = tf.argmax(conv8, dimension=3, name="prediction1")
deconv_shape1 = self.image_net["pool4"].get_shape()
W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, self.n_classes], name="W_t1")
b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1")
conv_t1 = utils.conv2d_transpose_strided(conv8, W_t1, b_t1, output_shape=tf.shape(self.image_net["pool4"]))
fuse_1 = tf.add(conv_t1, self.image_net["pool4"], name="fuse_1")
deconv_shape2 = self.image_net["pool3"].get_shape()
W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, deconv_shape1[3].value], name="W_t2")
b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
conv_t2 = utils.conv2d_transpose_strided(fuse_1, W_t2, b_t2, output_shape=tf.shape(self.image_net["pool3"]))
fuse_2 = tf.add(conv_t2, self.image_net["pool3"], name="fuse_2")
shape = tf.shape(image)
#deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], self.n_classes])
deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], 3 * (self.n_classes - 1)])
W_t3 = utils.weight_variable([16, 16, 3 * (self.n_classes - 1), deconv_shape2[3].value], name="W_t3")
b_t3 = utils.bias_variable([3 * (self.n_classes - 1)], name="b_t3")
conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=deconv_shape3, stride=8)
#tanh_t3 = tf.math.sigmoid(conv_t3)
for i in range(0, 3 * (self.n_classes - 1), 3):
current = tf.math.sigmoid(conv_t3[:, :, :, i:i+2])
if i == 0:
tanh_t3 = current
else:
tanh_t3 = tf.concat([tanh_t3, current], axis=-1)
tanh_t3 = tf.concat([tanh_t3, tf.nn.relu(conv_t3[:, :, :, i+2:i+3])], axis=-1)
return tanh_t3
def inference_res(input_image):
W1 = utils.weight_variable([3, 3, 3, 32])
b1 = utils.bias_variable([32])
hconv_1 = tf.nn.relu(utils.conv2d_basic(input_image, W1, b1))
h_norm = utils.local_response_norm(hconv_1)
bottleneck_1 = utils.bottleneck_unit(h_norm, 16, 16, down_stride=True, name="res_1")
bottleneck_2 = utils.bottleneck_unit(bottleneck_1, 8, 8, down_stride=True, name="res_2")
bottleneck_3 = utils.bottleneck_unit(bottleneck_2, 16, 16, up_stride=True, name="res_3")
bottleneck_4 = utils.bottleneck_unit(bottleneck_3, 32, 32, up_stride=True, name="res_4")
W5 = utils.weight_variable([3, 3, 32, 3])
b5 = utils.bias_variable([3])
out = tf.nn.tanh(utils.conv2d_basic(bottleneck_4, W5, b5))
return out
def vgg_net(weights, image):
layers = ('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
#grayiterstart = 0
if GRAY_MODE:
i = 0
name = 'conv1_1' # layers[0]
kind = name[:4] #=conv
bias = weights[0][0][0][0][0][1]
kernels = weights[0][0][0][0][0][0]
#put the in_channels first, select 1st channel
#[w,h,in_channels,out_channels]
kernelstrans = np.array([np.transpose(kernels, (2, 0, 1, 3))[0]])
#[in_channels,w,h,out_channels]
kernels = np.transpose(kernelstrans, (2, 1, 0, 3))
#after line above : [h,w,in_channels,out_channels]
kernels = utils.get_variable(kernels, name=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
#
for i, name in enumerate(layers):
kind = name[:4]
if kind == 'conv':
kernels, bias = weights[i + 1][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=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
if FLAGS.debug:
utils.add_activation_summary(current)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net
def inference_conv(image):
# incomplete :/
image_reshaped = tf.reshape(image, [-1, IMAGE_SIZE, IMAGE_SIZE, 1])
with tf.name_scope("conv1") as scope:
W_conv1 = utils.weight_variable([3, 3, 1, 32], name="W_conv1")
b_conv1 = utils.bias_variable([32], name="b_conv1")
add_to_reg_loss_and_summary(W_conv1, b_conv1)
h_conv1 = tf.nn.tanh(utils.conv2d_basic(image_reshaped, W_conv1, b_conv1))
with tf.name_scope("conv2") as scope:
W_conv2 = utils.weight_variable([3, 3, 32, 64], name="W_conv2")
b_conv2 = utils.bias_variable([64], name="b_conv2")
add_to_reg_loss_and_summary(W_conv2, b_conv2)
h_conv2 = tf.nn.tanh(utils.conv2d_strided(h_conv1, W_conv2, b_conv2))
with tf.name_scope("conv3") as scope:
W_conv3 = utils.weight_variable([3, 3, 64, 128], name="W_conv3")
b_conv3 = utils.bias_variable([128], name="b_conv3")
add_to_reg_loss_and_summary(W_conv3, b_conv3)
h_conv3 = tf.nn.tanh(utils.conv2d_strided(h_conv2, W_conv3, b_conv3))
with tf.name_scope("conv4") as scope:
W_conv4 = utils.weight_variable([3, 3, 128, 256], name="W_conv4")
b_conv4 = utils.bias_variable([256], name="b_conv4")
add_to_reg_loss_and_summary(W_conv4, b_conv4)
h_conv4 = tf.nn.tanh(utils.conv2d_strided(h_conv3, W_conv4, b_conv4))
def vgg_net(weights, image):
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]
kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)),
name=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net
def inference_conv(image):
# incomplete :/
image_reshaped = tf.reshape(image, [-1, IMAGE_SIZE, IMAGE_SIZE, 1])
with tf.name_scope("conv1") as scope:
W_conv1 = utils.weight_variable([3, 3, 1, 32], name="W_conv1")
b_conv1 = utils.bias_variable([32], name="b_conv1")
add_to_reg_loss_and_summary(W_conv1, b_conv1)
h_conv1 = tf.nn.tanh(
utils.conv2d_basic(image_reshaped, W_conv1, b_conv1))
with tf.name_scope("conv2") as scope:
W_conv2 = utils.weight_variable([3, 3, 32, 64], name="W_conv2")
b_conv2 = utils.bias_variable([64], name="b_conv2")
add_to_reg_loss_and_summary(W_conv2, b_conv2)
h_conv2 = tf.nn.tanh(utils.conv2d_strided(h_conv1, W_conv2, b_conv2))
with tf.name_scope("conv3") as scope:
W_conv3 = utils.weight_variable([3, 3, 64, 128], name="W_conv3")
b_conv3 = utils.bias_variable([128], name="b_conv3")
add_to_reg_loss_and_summary(W_conv3, b_conv3)
h_conv3 = tf.nn.tanh(utils.conv2d_strided(h_conv2, W_conv3, b_conv3))
with tf.name_scope("conv4") as scope:
W_conv4 = utils.weight_variable([3, 3, 128, 256], name="W_conv4")
b_conv4 = utils.bias_variable([256], name="b_conv4")
add_to_reg_loss_and_summary(W_conv4, b_conv4)
h_conv4 = tf.nn.tanh(utils.conv2d_strided(h_conv3, W_conv4, b_conv4))
def inference_resnet(dataset):
dataset_reshaped = tf.reshape(dataset, [-1, 28, 28, 1])
with tf.name_scope("conv1") as scope:
W_conv1 = utils.weight_variable([5, 5, 1, 32], name="W_conv1")
bias1 = utils.bias_variable([32], name="bias1")
tf.histogram_summary("W_conv1", W_conv1)
tf.histogram_summary("bias1", bias1)
h_conv1 = tf.nn.relu(
utils.conv2d_basic(dataset_reshaped, W_conv1, bias1))
h_norm1 = utils.local_response_norm(h_conv1)
bottleneck_1 = utils.bottleneck_unit(h_norm1,
32,
32,
down_stride=True,
name="res1")
bottleneck_2 = utils.bottleneck_unit(bottleneck_1,
64,
64,
down_stride=True,
name="res2")
with tf.name_scope("fc1") as scope:
h_flat = tf.reshape(bottleneck_2, [-1, 7 * 7 * 64])
W_fc1 = utils.weight_variable([7 * 7 * 64, 10], name="W_fc1")
bias_fc1 = utils.bias_variable([10], name="bias_fc1")
tf.histogram_summary("W_fc1", W_fc1)
tf.histogram_summary("bias_fc1", bias_fc1)
logits = tf.matmul(h_flat, W_fc1) + bias_fc1
return logits
def vgg_net(weights, image):
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 = np.transpose(kernels, (1, 0, 2, 3))
bias = bias.reshape(-1)
current = utils.conv2d_basic(current, kernels, bias)
elif kind == 'relu':
current = tf.nn.relu(current)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
assert len(net) == len(layers)
return net
def inference(image, keep_prob):
"""
Semantic segmentation network definition
:param image: input image. Should have values in range 0-255
:param keep_prob:
:return:
"""
print("setting up vgg initialized conv layers ...")
model_data = utils.get_model_data(FLAGS.model_dir, FLAGS.MODEL_NAME)
#mean = model_data['normalization'][0][0][0]
#mean_pixel = np.mean(mean, axis=(0, 1))
weights = np.squeeze(model_data['params'][0])
#processed_image = utils.process_image(image, mean_pixel)
with tf.variable_scope("inference"):
image_net = res_net(weights, image)
#conv_final_layer = image_net["res5c"]
conv_final_layer = image_net
fc_w = utils.weight_variable([1, 1, 2048, FLAGS.NUM_OF_CLASSESS],
name="fc_w")
fc_b = utils.bias_variable([FLAGS.NUM_OF_CLASSESS], name="fc_b")
fc = utils.conv2d_basic(conv_final_layer, fc_w, fc_b)
fc_dropout = tf.nn.dropout(fc, keep_prob)
logits = tf.squeeze(fc_dropout, [1, 2])
#logits = tf.squeeze(utils.conv2d_basic(conv_final_layer, fc_w, fc_b), [1,2])
print('logits shape', logits.shape)
annotation_pred = tf.argmax(logits, dimension=1, name="prediction")
return tf.expand_dims(annotation_pred, dim=1), logits
def vgg_net(weights, image):
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]
# Convolution 레이어일 경우
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]
# MATLAB 파일의 행렬 순서를 tensorflow 행렬의 순서로 변환합니다.
kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)),
name=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
# Activation 레이어일 경우
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
# Pooling 레이어일 경우
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net
def vgg_net(weights, image):
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=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
if FLAGS.debug:
utils.add_activation_summary(current)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net
def conv_layer(input, r_field, input_c, out_c, nr):
W = utils.weight_variable([r_field, r_field, input_c, out_c],
name="W" + str(nr))
b = utils.bias_variable([out_c], name="b" + str(nr))
conv = utils.conv2d_basic(input, W, b, name="conv" + str(nr))
relu = tf.nn.relu(conv, name="relu" + str(nr))
return relu
def build_labels_layers(self, image, keep_prob):
with tf.variable_scope("labels"):
pool5 = utils.max_pool_2x2(self.image_net["conv5_3"])
W6 = utils.weight_variable([7, 7, 512, 4096], name="W6")
b6 = utils.bias_variable([4096], name="b6")
conv6 = utils.conv2d_basic(pool5, W6, b6)
relu6 = tf.nn.relu(conv6, name="relu6")
if self.debug:
utils.add_activation_summary(relu6)
relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob)
W7 = utils.weight_variable([1, 1, 4096, 4096], name="W7")
b7 = utils.bias_variable([4096], name="b7")
conv7 = utils.conv2d_basic(relu_dropout6, W7, b7)
relu7 = tf.nn.relu(conv7, name="relu7")
if self.debug:
utils.add_activation_summary(relu7)
relu_dropout7 = tf.nn.dropout(relu7, keep_prob=keep_prob)
W8 = utils.weight_variable([1, 1, 4096, self.n_classes], name="W8")
b8 = utils.bias_variable([self.n_classes], name="b8")
conv8 = utils.conv2d_basic(relu_dropout7, W8, b8)
# annotation_pred1 = tf.argmax(conv8, dimension=3, name="prediction1")
deconv_shape1 = self.image_net["pool4"].get_shape()
W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, self.n_classes], name="W_t1")
b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1")
conv_t1 = utils.conv2d_transpose_strided(conv8, W_t1, b_t1, output_shape=tf.shape(self.image_net["pool4"]))
fuse_1 = tf.add(conv_t1, self.image_net["pool4"], name="fuse_1")
deconv_shape2 = self.image_net["pool3"].get_shape()
W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, deconv_shape1[3].value], name="W_t2")
b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
conv_t2 = utils.conv2d_transpose_strided(fuse_1, W_t2, b_t2, output_shape=tf.shape(self.image_net["pool3"]))
fuse_2 = tf.add(conv_t2, self.image_net["pool3"], name="fuse_2")
shape = tf.shape(image)
deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], self.n_classes])
W_t3 = utils.weight_variable([16, 16, self.n_classes, deconv_shape2[3].value], name="W_t3")
b_t3 = utils.bias_variable([self.n_classes], name="b_t3")
conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=deconv_shape3, stride=8)
annotation_pred = tf.argmax(conv_t3, dimension=3, name="prediction")
return tf.expand_dims(annotation_pred, dim=3), conv_t3
def vgg_net(weights, image):
layers = (
'conv1_1',
'relu1_1',
'conv1_2',
'relu1_2',
'pool1', # output: 112*112*64
'conv2_1',
'relu2_1',
'conv2_2',
'relu2_2',
'pool2', # output: 56*56*128
'conv3_1',
'relu3_1',
'conv3_2',
'relu3_2',
'conv3_3', # output: 28*28*256
'relu3_3',
'conv3_4',
'relu3_4',
'pool3',
'conv4_1',
'relu4_1',
'conv4_2',
'relu4_2',
'conv4_3', # output: 14*14*512
'relu4_3',
'conv4_4',
'relu4_4',
'pool4',
'conv5_1',
'relu5_1',
'conv5_2',
'relu5_2',
'conv5_3', # output: 7*7*512
'relu5_3',
'conv5_4',
'relu5_4') # followed by three FN
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=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net
def generator(images, train_phase):
print("setting up vgg initialized conv layers ...")
model_data = utils.get_model_data(FLAGS.model_dir, MODEL_URL)
weights = np.squeeze(model_data['layers'])
with tf.variable_scope("generator") as scope:
W0 = utils.weight_variable([3, 3, 1, 64], name="W0")
b0 = utils.bias_variable([64], name="b0")
conv0 = utils.conv2d_basic(images, W0, b0)
hrelu0 = tf.nn.relu(conv0, name="relu")
image_net = vgg_net(weights, hrelu0)
vgg_final_layer = image_net["relu5_3"]
pool5 = utils.max_pool_2x2(vgg_final_layer)
# now to upscale to actual image size
deconv_shape1 = image_net["pool4"].get_shape()
W_t1 = utils.weight_variable(
[4, 4, deconv_shape1[3].value,
pool5.get_shape()[3].value],
name="W_t1")
b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1")
conv_t1 = utils.conv2d_transpose_strided(pool5,
W_t1,
b_t1,
output_shape=tf.shape(
image_net["pool4"]))
fuse_1 = tf.add(conv_t1, image_net["pool4"], name="fuse_1")
deconv_shape2 = image_net["pool3"].get_shape()
W_t2 = utils.weight_variable(
[4, 4, deconv_shape2[3].value, deconv_shape1[3].value],
name="W_t2")
b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
conv_t2 = utils.conv2d_transpose_strided(fuse_1,
W_t2,
b_t2,
output_shape=tf.shape(
image_net["pool3"]))
fuse_2 = tf.add(conv_t2, image_net["pool3"], name="fuse_2")
shape = tf.shape(images)
deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], 2])
W_t3 = utils.weight_variable([16, 16, 2, deconv_shape2[3].value],
name="W_t3")
b_t3 = utils.bias_variable([2], name="b_t3")
pred = utils.conv2d_transpose_strided(fuse_2,
W_t3,
b_t3,
output_shape=deconv_shape3,
stride=8)
# return tf.concat(concat_dim=3, values=[images, pred], name="pred_image")
return tf.concat([images, pred], 3, "pred_image")
def vgg_net(weights, image):
# def vgg_net(image):
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 # [n,224,224,3]
for i, name in enumerate(layers):
kind = name[:4]
# kind2=name[:5]
if kind=='conv':#kind2 == 'conv1':
# '''
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=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
'''
current=tf.layers.conv2d(current,64,3,padding='same')
elif kind2=='conv2':
current = tf.layers.conv2d(current, 128, 3, padding='same')
elif kind2=='conv3':
current = tf.layers.conv2d(current, 256, 3, padding='same')
elif kind2=='conv4':
current = tf.layers.conv2d(current, 512, 3, padding='same')
elif kind2=='conv5':
current = tf.layers.conv2d(current, 512, 3, padding='same')
else:
pass
# '''
if kind == 'relu':
current = tf.nn.relu(current, name=name)
if FLAGS.debug:
utils.add_activation_summary(current)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net # [n,14,14,512]
def inference_strided(input_image):
W1 = utils.weight_variable([9, 9, 3, 32])
b1 = utils.bias_variable([32])
tf.histogram_summary("W1", W1)
tf.histogram_summary("b1", b1)
h_conv1 = tf.nn.relu(utils.conv2d_basic(input_image, W1, b1))
W2 = utils.weight_variable([3, 3, 32, 64])
b2 = utils.bias_variable([64])
tf.histogram_summary("W2", W2)
tf.histogram_summary("b2", b2)
h_conv2 = tf.nn.relu(utils.conv2d_strided(h_conv1, W2, b2))
W3 = utils.weight_variable([3, 3, 64, 128])
b3 = utils.bias_variable([128])
tf.histogram_summary("W3", W3)
tf.histogram_summary("b3", b3)
h_conv3 = tf.nn.relu(utils.conv2d_strided(h_conv2, W3, b3))
# upstrides
W4 = utils.weight_variable([3, 3, 64, 128])
b4 = utils.bias_variable([64])
tf.histogram_summary("W4", W4)
tf.histogram_summary("b4", b4)
# print h_conv3.get_shape()
# print W4.get_shape()
h_conv4 = tf.nn.relu(utils.conv2d_transpose_strided(h_conv3, W4, b4))
W5 = utils.weight_variable([3, 3, 32, 64])
b5 = utils.bias_variable([32])
tf.histogram_summary("W5", W5)
tf.histogram_summary("b5", b5)
h_conv5 = tf.nn.relu(utils.conv2d_transpose_strided(h_conv4, W5, b5))
W6 = utils.weight_variable([9, 9, 32, 3])
b6 = utils.bias_variable([3])
tf.histogram_summary("W6", W6)
tf.histogram_summary("b6", b6)
pred_image = tf.nn.tanh(utils.conv2d_basic(h_conv5, W6, b6))
return pred_image
def inferece(dataset, prob):
with tf.name_scope("conv1") as scope:
W_conv1 = utils.weight_variable([5, 5, 1, 32])
b_conv1 = utils.bias_variable([32])
tf.histogram_summary("W_conv1", W_conv1)
tf.histogram_summary("b_conv1", b_conv1)
h_conv1 = utils.conv2d_basic(dataset, W_conv1, b_conv1)
h_1 = tf.nn.relu(h_conv1)
h_pool1 = utils.max_pool_2x2(h_1)
add_to_regularization_loss(W_conv1, b_conv1)
with tf.name_scope("conv2") as scope:
W_conv2 = utils.weight_variable([3, 3, 32, 64])
b_conv2 = utils.bias_variable([64])
tf.histogram_summary("W_conv2", W_conv2)
tf.histogram_summary("b_conv2", b_conv2)
h_conv2 = utils.conv2d_basic(h_pool1, W_conv2, b_conv2)
h_2 = tf.nn.relu(h_conv2)
h_pool2 = utils.max_pool_2x2(h_2)
add_to_regularization_loss(W_conv2, b_conv2)
with tf.name_scope("fc_1") as scope:
image_size = IMAGE_SIZE / 4
h_flat = tf.reshape(h_pool2, [-1, image_size * image_size * 64])
W_fc1 = utils.weight_variable([image_size * image_size * 64, 256])
b_fc1 = utils.bias_variable([256])
tf.histogram_summary("W_fc1", W_fc1)
tf.histogram_summary("b_fc1", b_fc1)
h_fc1 = tf.nn.relu(tf.matmul(h_flat, W_fc1) + b_fc1)
h_fc1_dropout = tf.nn.dropout(h_fc1, prob)
with tf.name_scope("fc_2") as scope:
W_fc2 = utils.weight_variable([256, NUM_LABELS])
b_fc2 = utils.bias_variable([NUM_LABELS])
tf.histogram_summary("W_fc2", W_fc2)
tf.histogram_summary("b_fc2", b_fc2)
pred = tf.matmul(h_fc1, W_fc2) + b_fc2
return pred
def inferece(dataset, prob):
with tf.name_scope("conv1") as scope:
W_conv1 = utils.weight_variable([5, 5, 1, 32])
b_conv1 = utils.bias_variable([32])
tf.histogram_summary("W_conv1", W_conv1)
tf.histogram_summary("b_conv1", b_conv1)
h_conv1 = utils.conv2d_basic(dataset, W_conv1, b_conv1)
h_1 = tf.nn.relu(h_conv1)
h_pool1 = utils.max_pool_2x2(h_1)
add_to_regularization_loss(W_conv1, b_conv1)
with tf.name_scope("conv2") as scope:
W_conv2 = utils.weight_variable([3, 3, 32, 64])
b_conv2 = utils.bias_variable([64])
tf.histogram_summary("W_conv2", W_conv2)
tf.histogram_summary("b_conv2", b_conv2)
h_conv2 = utils.conv2d_basic(h_pool1, W_conv2, b_conv2)
h_2 = tf.nn.relu(h_conv2)
h_pool2 = utils.max_pool_2x2(h_2)
add_to_regularization_loss(W_conv2, b_conv2)
with tf.name_scope("fc_1") as scope:
image_size = IMAGE_SIZE / 4
h_flat = tf.reshape(h_pool2, [-1, image_size * image_size * 64])
W_fc1 = utils.weight_variable([image_size * image_size * 64, 256])
b_fc1 = utils.bias_variable([256])
tf.histogram_summary("W_fc1", W_fc1)
tf.histogram_summary("b_fc1", b_fc1)
h_fc1 = tf.nn.relu(tf.matmul(h_flat, W_fc1) + b_fc1)
h_fc1_dropout = tf.nn.dropout(h_fc1, prob)
with tf.name_scope("fc_2") as scope:
W_fc2 = utils.weight_variable([256, NUM_LABELS])
b_fc2 = utils.bias_variable([NUM_LABELS])
tf.histogram_summary("W_fc2", W_fc2)
tf.histogram_summary("b_fc2", b_fc2)
pred = tf.matmul(h_fc1, W_fc2) + b_fc2
return pred
def vgg_net(weights, image):
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=name + "_w")
bias = Utils.get_variable(bias.reshape(-1), name=name + "_b")
current = Utils.conv2d_basic(current, kernels, bias) # 前向传播结果 current
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
# if FLAGS.debug:
# util.add_activation_summary(current)
elif kind == 'pool':
# vgg 的前5层的stride都是2，也就是前5层的size依次减小1倍
# 这里处理了前4层的stride，用的是平均池化
# 第5层的pool在下文的外部处理了，用的是最大池化
# pool1 size缩小2倍
# pool2 size缩小4倍
# pool3 size缩小8倍
# pool4 size缩小16倍
current = Utils.avg_pool_2x2(current)
net[name] = current
# added for resume better
global_iter_counter = tf.Variable(0, name='global_step', trainable=False)
net['global_step'] = global_iter_counter # 每层前向传播结果放在net中， 是一个字典
return net
def vgg_net(weights, image):
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]
if (name == 'conv1_1'):
kernel_shape = kernels.shape[:2] + (4, ) + kernels.shape[3:]
else:
kernel_shape = kernels.shape
bias_shape = bias.shape
# matconvnet: weights are [width, height, in_channels, out_channels]
# tensorflow: weights are [height, width, in_channels, out_channels]
new_kernel = np.zeros(kernel_shape)
new_kernel_shape = np.transpose(new_kernel, (1, 0, 2, 3)).shape
# print(f"new kernel shape: {new_kernel_shape}")
new_bias = np.zeros(bias_shape)
new_bias_shape = new_bias.reshape(-1).shape[0]
# print(f"new bias shape: {new_bias_shape}")
kernels = utils.weight_variable(shape=new_kernel_shape, name=name + "_w" )
bias = utils.bias_variable(shape=[new_bias_shape], name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
if FLAGS.debug:
utils.add_activation_summary(current)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
# print(f"VGG-19 {name} layer: {current.shape}")
return net
def inference(self, images, inference_name, channel, keep_prob):
"""
Semantic segmentation network definition
:param image: input image. Should have values in range 0-255
:param keep_prob:
:return:
"""
print("setting up resnet101 initialized conv layers ...")
#mean_pixel = np.mean(mean, axis=(0, 1))
processed_images = utils.process_image(images, cfgs.mean_pixel)
processed_images = tf.nn.dropout(processed_images, self.input_keep_prob)
with tf.variable_scope(inference_name):
conv1 = utils_layers.conv2d_layer(processed_images, '1', [7, 7, cfgs.cur_channel+cfgs.seq_num, 64], pool_=3)
#Resnet
conv_final_layer, image_net = self.resnet.resnet_op(conv1, if_avg_pool=0)
#dropout
conv_final_layer = tf.nn.dropout(conv_final_layer, keep_prob)
W_last = utils.weight_variable([1, 1, 2048, 2], name='W_last')
b_last = utils.bias_variable([2], name='b8')
conv_last = utils.conv2d_basic(conv_final_layer, W_last, b_last)
print('conv_last: ', conv_last.get_shape())
#Deconv operator
#1. output_shape=[self.batch_size, 14, 14, 1024]
conv_t1 = utils_layers.deconv2d_layer(conv_last, 't1', [4,4,1024,2], output_shape=tf.shape(image_net['block3_b22']))
fuse_1 = tf.add(conv_t1, image_net['block3_b22'], name="fuse_1")
#2. output_shape=[self.batch_size, 28, 28, 512]
conv_t2 = utils_layers.deconv2d_layer(fuse_1, 't2', [4,4,512,1024], output_shape=tf.shape(image_net['block2_b3']))
fuse_2 = tf.add(conv_t2, image_net['block2_b3'], name="fuse_2")
#3. output_shape = [self.batch_size, 56, 56, 256]
conv_t3 = utils_layers.deconv2d_layer(fuse_2, 't3', [4,4,256,512], output_shape=tf.shape(image_net['block1_b2']))
fuse_3 = tf.add(conv_t3, image_net['block1_b2'], name='fuse_3')
#4. output_shape=[self.batch_size, 224, 224, 2]
shape = tf.shape(images)
conv_t4 = utils_layers.deconv2d_layer(fuse_3, 't4', [16, 16, 2, 256], output_shape=[shape[0], shape[1], shape[2], 2], stride=4)
annotation_pred = tf.argmax(conv_t4, dimension=3, name="prediction")
logits = conv_t4
print('logits shape', logits.shape)
return logits
def inference_fully_convolutional(dataset):
'''
Fully convolutional inference on notMNIST dataset
:param datset: [batch_size, 28*28*1] tensor
:return: logits
'''
dataset_reshaped = tf.reshape(dataset, [-1, 28, 28, 1])
with tf.name_scope("conv1") as scope:
W_conv1 = utils.weight_variable_xavier_initialized([3, 3, 1, 32],
name="W_conv1")
b_conv1 = utils.bias_variable([32], name="b_conv1")
h_conv1 = tf.nn.relu(
utils.conv2d_strided(dataset_reshaped, W_conv1, b_conv1))
with tf.name_scope("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 = tf.nn.relu(utils.conv2d_strided(h_conv1, W_conv2, b_conv2))
with tf.name_scope("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 = tf.nn.relu(utils.conv2d_strided(h_conv2, W_conv3, b_conv3))
with tf.name_scope("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 = tf.nn.relu(utils.conv2d_strided(h_conv3, W_conv4, b_conv4))
with tf.name_scope("conv5") as scope:
# W_conv5 = utils.weight_variable_xavier_initialized([2, 2, 256, 512], name="W_conv5")
# b_conv5 = utils.bias_variable([512], name="b_conv5")
# h_conv5 = tf.nn.relu(utils.conv2d_strided(h_conv4, W_conv5, b_conv5))
h_conv5 = utils.avg_pool_2x2(h_conv4)
with tf.name_scope("conv6") as scope:
W_conv6 = utils.weight_variable_xavier_initialized([1, 1, 256, 10],
name="W_conv6")
b_conv6 = utils.bias_variable([10], name="b_conv6")
logits = tf.nn.relu(utils.conv2d_basic(h_conv5, W_conv6, b_conv6))
print logits.get_shape()
logits = tf.reshape(logits, [-1, 10])
return logits
def inference(image, keep_prob):
"""
Semantic segmentation network definition
:param image: input image. Should have values in range 0-255
:param keep_prob:
:return:
"""
print("setting up vgg initialized conv layers ...")
model_data = utils.get_model_data(FLAGS.model_dir, MODEL_URL)
mean = model_data['normalization'][0][0][0]
mean_pixel = np.mean(mean, axis=(0, 1))
weights = np.squeeze(model_data['layers'])
processed_image = utils.process_image(image, mean_pixel)
with tf.variable_scope("inference"):
vgg_end_layer = 'conv4_4'
image_net = vgg_net(weights, processed_image, end_layer=vgg_end_layer)
conv_final_layer = image_net[vgg_end_layer]
dropout = tf.nn.dropout(conv_final_layer, keep_prob=keep_prob)
W_final = utils.weight_variable([1, 1, 512, NUM_OF_CLASSES], name="W_final")
b_final = utils.bias_variable([NUM_OF_CLASSES], name="b_final")
conv_final = utils.conv2d_basic(dropout, W_final, b_final)
if FLAGS.debug:
utils.add_activation_summary(conv_final)
# now to upscale to actual image size
deconv_shape2 = image_net["pool2"].get_shape()
W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, NUM_OF_CLASSES], name="W_t2")
b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
conv_t2 = utils.conv2d_transpose_strided(conv_final, W_t2, b_t2, output_shape=tf.shape(image_net["pool2"]))
fuse_2 = tf.add(conv_t2, image_net["pool2"], name="fuse_2")
shape = tf.shape(image)
deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], NUM_OF_CLASSES])
W_t3 = utils.weight_variable([8, 8, NUM_OF_CLASSES, deconv_shape2[3].value], name="W_t3")
b_t3 = utils.bias_variable([NUM_OF_CLASSES], name="b_t3")
conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=deconv_shape3, stride=4)
annotation_pred = tf.argmax(conv_t3, axis=3, name="prediction", output_type=tf.int32)
return tf.expand_dims(annotation_pred, axis=3), conv_t3
def vgg_net(weights, image):
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] # layer的类型,是conv还是relu或者pool.
if kind == 'conv':
kernels, bias = weights[i][0][0][0][0]
kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)), name=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
if name[4:5] == '5': # conv5开始使用atrous_conv2d卷积.
current = utils.atrous_conv2d_basic(current, kernels, bias, 2) # rate=2,也即pad=2.
current = utils.batch_norm_layer(current, FLAGS.mode, scope_bn=name) # BN处理.
else: # conv1-4
current = utils.conv2d_basic(current, kernels, bias)
current = utils.batch_norm_layer(current, FLAGS.mode, scope_bn=name) # BN处理.
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
if FLAGS.debug:
utils.add_activation_summary(current)
elif kind == 'pool':
if name[4:5] == '4':
current = utils.max_pool_1x1(current)
else:
current = utils.max_pool_3x3(current)
net[name] = current
return net
def inference_fully_convolutional(dataset):
'''
Fully convolutional inference on notMNIST dataset
:param datset: [batch_size, 28*28*1] tensor
:return: logits
'''
dataset_reshaped = tf.reshape(dataset, [-1, 28, 28, 1])
with tf.name_scope("conv1") as scope:
W_conv1 = utils.weight_variable_xavier_initialized([3, 3, 1, 32], name="W_conv1")
b_conv1 = utils.bias_variable([32], name="b_conv1")
h_conv1 = tf.nn.relu(utils.conv2d_strided(dataset_reshaped, W_conv1, b_conv1))
with tf.name_scope("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 = tf.nn.relu(utils.conv2d_strided(h_conv1, W_conv2, b_conv2))
with tf.name_scope("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 = tf.nn.relu(utils.conv2d_strided(h_conv2, W_conv3, b_conv3))
with tf.name_scope("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 = tf.nn.relu(utils.conv2d_strided(h_conv3, W_conv4, b_conv4))
with tf.name_scope("conv5") as scope:
# W_conv5 = utils.weight_variable_xavier_initialized([2, 2, 256, 512], name="W_conv5")
# b_conv5 = utils.bias_variable([512], name="b_conv5")
# h_conv5 = tf.nn.relu(utils.conv2d_strided(h_conv4, W_conv5, b_conv5))
h_conv5 = utils.avg_pool_2x2(h_conv4)
with tf.name_scope("conv6") as scope:
W_conv6 = utils.weight_variable_xavier_initialized([1, 1, 256, 10], name="W_conv6")
b_conv6 = utils.bias_variable([10], name="b_conv6")
logits = tf.nn.relu(utils.conv2d_basic(h_conv5, W_conv6, b_conv6))
print logits.get_shape()
logits = tf.reshape(logits, [-1, 10])
return logits
def vgg_net(weights, image):
# VGG网络前五大部分
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 # 预测图像
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=name + "_w") # conv1_1_w
bias = utils.get_variable(bias.reshape(-1),
name=name + "_b") # conv1_1_b
current = utils.conv2d_basic(current, kernels,
bias) # 前向传播结果 current
elif kind == 'relu':
current = tf.nn.relu(current, name=name) # relu1_1
if FLAGS.debug: # 是否开启debug模式 true / false
utils.add_activation_summary(current) # 画图
elif kind == 'pool':
# vgg 的前5层的stride都是2，也就是前5层的size依次减小1倍
# 这里处理了前4层的stride，用的是平均池化
# 第5层的pool在下文的外部处理了，用的是最大池化
# pool1 size缩小2倍
# pool2 size缩小4倍
# pool3 size缩小8倍
# pool4 size缩小16倍
current = utils.avg_pool_2x2(current)
net[name] = current # 每层前向传播结果放在net中， 是一个字典
return net
def vgg_net(weights, image):
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):
if name in ['conv3_4', 'relu3_4', 'conv4_4', 'relu4_4', 'conv5_4', 'relu5_4']:
continue
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=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
if FLAGS.debug:
utils.add_activation_summary(current)
elif kind == 'pool':
current = utils.avg_pool_2x2(current)
net[name] = current
return net
def inference(image, keep_prob):
"""
Semantic segmentation network definition
:param image: input image. Should have values in range 0-255
:param keep_prob:
:return:
"""
print("setting up vgg initialized conv layers ...")
model_data = utils.get_model_data(FLAGS.model_dir, MODEL_URL)
mean = model_data['normalization'][0][0][0]
mean_pixel = np.mean(mean, axis=(0, 1))
weights = np.squeeze(model_data['layers'])
#processed_image = utils.process_image(image, mean_pixel)
with tf.variable_scope("inference"):
image_net = vgg_net(weights, image)
conv_final_layer = image_net["conv5_3"]
pool5 = utils.max_pool_2x2(conv_final_layer)
W6 = utils.weight_variable([7, 7, 512, 4096], name="W6")
b6 = utils.bias_variable([4096], name="b6")
conv6 = utils.conv2d_basic(pool5, W6, b6)
relu6 = tf.nn.relu(conv6, name="relu6")
if FLAGS.debug:
utils.add_activation_summary(relu6)
relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob)
W7 = utils.weight_variable([1, 1, 4096, 4096], name="W7")
b7 = utils.bias_variable([4096], name="b7")
conv7 = utils.conv2d_basic(relu_dropout6, W7, b7)
relu7 = tf.nn.relu(conv7, name="relu7")
if FLAGS.debug:
utils.add_activation_summary(relu7)
relu_dropout7 = tf.nn.dropout(relu7, keep_prob=keep_prob)
W8 = utils.weight_variable([1, 1, 4096, NUM_OF_CLASSESS], name="W8")
b8 = utils.bias_variable([NUM_OF_CLASSESS], name="b8")
conv8 = utils.conv2d_basic(relu_dropout7, W8, b8)
# annotation_pred1 = tf.argmax(conv8, dimension=3, name="prediction1")
# now to upscale to actual image size
deconv_shape1 = image_net["pool4"].get_shape()
W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, NUM_OF_CLASSESS], name="W_t1")
b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1")
conv_t1 = utils.conv2d_transpose_strided(conv8, W_t1, b_t1, output_shape=tf.shape(image_net["pool4"]))
fuse_1 = tf.add(conv_t1, image_net["pool4"], name="fuse_1")
deconv_shape2 = image_net["pool3"].get_shape()
W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, deconv_shape1[3].value], name="W_t2")
b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
conv_t2 = utils.conv2d_transpose_strided(fuse_1, W_t2, b_t2, output_shape=tf.shape(image_net["pool3"]))
fuse_2 = tf.add(conv_t2, image_net["pool3"], name="fuse_2")
shape = tf.shape(image)
deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], NUM_OF_CLASSESS])
W_t3 = utils.weight_variable([16, 16, NUM_OF_CLASSESS, deconv_shape2[3].value], name="W_t3")
b_t3 = utils.bias_variable([NUM_OF_CLASSESS], name="b_t3")
conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=deconv_shape3, stride=8)
annotation_pred = tf.argmax(conv_t3, dimension=3, name="prediction")
return tf.expand_dims(annotation_pred, dim=3), conv_t3
