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 resnet-101 pretrained layers ...")
resnet101_model = utils.get_model_data(FLAGS.model_dir)
weights = np.squeeze(resnet101_model['params'])
mean_pixel = resnet101_model['meta'][0][0][2][0][0][2]
normalised_img = utils.process_image(image, mean_pixel)
with tf.variable_scope("inference"):
net = resnet101_net(normalised_img, weights, keep_prob)
last_layer = net["res5c_relu"]
fc_filter = utils.weight_variable([1, 1, 2048, NUM_OF_CLASSES],
name="fc_filter")
fc_bias = utils.bias_variable([NUM_OF_CLASSES], name="fc_bias")
fc = tf.nn.bias_add(tf.nn.conv2d(last_layer,
fc_filter,
strides=[1, 1, 1, 1],
padding="SAME"),
fc_bias,
name='fc')
# now to upscale to actual image size
deconv_shape1 = net["res4b22_relu"].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(fc,
W_t1,
b_t1,
output_shape=tf.shape(
net["res4b22_relu"]))
fuse_1 = tf.add(conv_t1, net["res4b22_relu"], name="fuse_1")
deconv_shape2 = net["res3b3_relu"].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["res3b3_relu"]))
fuse_2 = tf.add(conv_t2, net["res3b3_relu"], 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(model_dir)
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_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