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]
if name == 'conv1_1':
np.random.seed(3796)
append_channels= np.random.normal(loc=0,scale=0.02,size=(3,3,2,64))
# print(append_channels)
kernels = np.concatenate((kernels, append_channels), axis=2)
kernels = utils.get_variable(kernels, name=name + "_w")
else:
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)
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)
mean = model_data['normalization'][0][0][0]
mean_pixel = np.mean(mean, axis=(0, 1))
mean_pixel = np.append(mean_pixel, [
30.6986130799, 284.97018, 106.314329243, 124.171918054, 109.260369903,
182.615729022, 75.1762766769, 84.3529895303, 100.699252985,
66.8837693324, 98.6030061849, 133.955897217
])
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)
# 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, axis=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 pretrained conv layers ...")
model_data = utils.get_model_data(FLAGS.model_dir)
mean_pixel_init = model_data['normalization'][0][0][0]
# mean_pixel_init = np.mean(mean, axis=(0, 1))
mean_pixel = np.zeros((IMAGE_SIZE, IMAGE_SIZE, 6))
mean_pixel[:, :, 0] = mean_pixel_init[:, :, 0]
mean_pixel[:, :, 1] = mean_pixel_init[:, :, 1]
mean_pixel[:, :, 2] = mean_pixel_init[:, :, 2]
mean_pixel[:, :, 3] = np.ones((IMAGE_SIZE, IMAGE_SIZE)) * 97.639895122076
mean_pixel[:, :, 4] = np.ones(
(IMAGE_SIZE, IMAGE_SIZE)) * 45.548982715963994
mean_pixel[:, :, 5] = np.ones((IMAGE_SIZE, IMAGE_SIZE)) * 37.69138
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_CLASSES], name="W8")
b8 = utils.bias_variable([NUM_OF_CLASSES], name="b8")
conv8 = utils.conv2d_basic(relu_dropout7, W8, b8)
annotation_pred1 = tf.argmax(conv8, axis=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_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(
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_CLASSES])
W_t3 = utils.weight_variable(
[16, 16, 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=8)
annotation_pred = tf.argmax(conv_t3, axis=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 pretrained conv layers ...")
model_data = utils.get_model_data(FLAGS.model_dir)
mean = model_data['normalization'][0][0][0]
mean_pixel = np.mean(mean, axis=(0, 1))
mean_pixel = np.append(mean_pixel, [30.69861307993539, 284.9702])
# mean_pixel = np.array([120.8952399852595, 81.93008162338278, 81.28988761879855, 30.69861307993539, 284.9702])
weights = np.squeeze(model_data['layers'])
processed_image = utils.process_image(image, mean_pixel)
with tf.variable_scope("inference"):
net = vgg_net(weights, processed_image)
conv_final_layer = 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_CLASSES], name="W8")
b8 = utils.bias_variable([NUM_OF_CLASSES], name="b8")
conv8 = utils.conv2d_basic(relu_dropout7, W8, b8)
annotation_pred1 = tf.argmax(conv8, axis=3, name="prediction1")
# now to upscale to actual image size
deconv_shape1 = net["pool4"].get_shape()
W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, NUM_OF_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(net["pool4"]))
fuse_1 = tf.add(conv_t1, net["pool4"], name="fuse_1")
deconv_shape2 = 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(net["pool3"]))
fuse_2 = tf.add(conv_t2, net["pool3"], name="fuse_2")
deconv_shape3 = net["pool2"].get_shape()
W_t3 = utils.weight_variable([4, 4, deconv_shape3[3].value, deconv_shape2[3].value], name="W_t3")
b_t3 = utils.bias_variable([deconv_shape3[3].value], name="b_t3")
conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=tf.shape(net["pool2"]))
fuse_3 = tf.add(conv_t3, net["pool2"], name="fuse_3")
shape = tf.shape(image)
deconv_shape4 = tf.stack([shape[0], shape[1], shape[2], NUM_OF_CLASSES])
W_t4 = utils.weight_variable([8, 8, NUM_OF_CLASSES, deconv_shape3[3].value], name="W_t4")
b_t4 = utils.bias_variable([NUM_OF_CLASSES], name="b_t4")
conv_t4 = utils.conv2d_transpose_strided(fuse_3, W_t4, b_t4, output_shape=deconv_shape4, stride=4)
annotation_pred = tf.argmax(conv_t4, axis=3, name="prediction")
return tf.expand_dims(annotation_pred, dim=3), conv_t4