def unet_road_detection(x, dropout, is_training, weight_decay, crop,
num_input_bands, num_classes, crop_size,
extract_features):
x = tf.reshape(x, shape=[-1, crop, crop, num_input_bands])
conv1_1 = _conv_layer(x, [3, 3, num_input_bands, 64],
"conv1_1",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='elu')
conv1_2 = _conv_layer(conv1_1, [3, 3, 64, 64],
"conv1_2",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='elu')
s_pool1 = crop_size
pool1 = _max_pool(conv1_2, [1, 2, 2, 1], [1, 2, 2, 1], 'pool1', pad='SAME')
conv2_1 = _conv_layer(pool1, [3, 3, 64, 128],
"conv2_1",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='elu')
conv2_2 = _conv_layer(conv2_1, [3, 3, 128, 128],
"conv2_2",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='elu')
s_pool2 = math.ceil(s_pool1 / float(2))
# s_pool2 = math.ceil(float(s_pool1 - 2 + 1) / float(2))
pool2 = _max_pool(conv2_2, [1, 2, 2, 1], [1, 2, 2, 1], 'pool2', pad='SAME')
conv3_1 = _conv_layer(pool2, [3, 3, 128, 256],
"conv3_1",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='elu')
conv3_2 = _conv_layer(conv3_1, [3, 3, 256, 256],
"conv3_2",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='elu')
s_pool3 = math.ceil(s_pool2 / float(2))
# s_pool3 = math.ceil(float(s_pool2 - 2 + 1) / float(2))
pool3 = _max_pool(conv3_2, [1, 2, 2, 1], [1, 2, 2, 1], 'pool3', pad='SAME')
conv4_1 = _conv_layer(pool3, [3, 3, 256, 512],
"conv4_1",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='elu')
conv4_2 = _conv_layer(conv4_1, [3, 3, 512, 512],
"conv4_2",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='elu')
# s_pool4 = math.ceil(s_pool3 / float(2))
# pool4 = _max_pool(conv4_2, [1, 2, 2, 1], [1, 2, 2, 1], 'pool4', pad='SAME')
#
# conv5_1 = _conv_layer(pool4, [3, 3, 512, 1024], "conv5_1", weight_decay, is_training,
# strides=[1, 1, 1, 1], pad='SAME', activation='elu')
# conv5_2 = _conv_layer(conv5_1, [3, 3, 1024, 1024], "conv5_2", weight_decay, is_training,
# strides=[1, 1, 1, 1], pad='SAME', activation='elu')
# ---------------------------------End of encoder----------------------------------
aspp = atrous_spatial_pyramid_pooling(conv4_2, [6, 12, 18], weight_decay,
is_training)
# deconv4_1 = _deconv_layer(aspp, [2, 2, 512, 1024], _get_shape(conv5_2), 'deconv4_1', weight_decay,
# [1, 2, 2, 1], pad='SAME', has_bias=True)
# # deconv4_2 = _crop_and_concat(conv2_2, deconv2_1, (s_pool2, s_pool2), (s_pool3*2, s_pool3*2))
# deconv4_2 = tf.concat(values=[conv4_2, deconv4_1], axis=-1)
# deconv4_3 = _conv_layer(deconv4_2, [3, 3, 1024, 512], "deconv4_3", weight_decay, is_training,
# strides=[1, 1, 1, 1], pad='SAME')
# deconv4_4 = _conv_layer(deconv4_3, [3, 3, 512, 512], "deconv4_4", weight_decay, is_training,
# strides=[1, 1, 1, 1], pad='SAME')
deconv3_1 = _deconv_layer(aspp, [2, 2, 256, 512],
_get_shape(conv4_2),
'deconv3_1',
weight_decay, [1, 2, 2, 1],
pad='SAME',
has_bias=True)
# deconv3_2 = _crop_and_concat(conv2_2, deconv2_1, (s_pool2, s_pool2), (s_pool3*2, s_pool3*2))
deconv3_2 = tf.concat(values=[conv3_2, deconv3_1], axis=-1)
deconv3_3 = _conv_layer(deconv3_2, [3, 3, 512, 256],
"deconv3_3",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
deconv3_4 = _conv_layer(deconv3_3, [3, 3, 256, 256],
"deconv3_4",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
deconv2_1 = _deconv_layer(deconv3_4, [2, 2, 128, 256],
_get_shape(conv3_2),
'deconv2_1',
weight_decay, [1, 2, 2, 1],
pad='SAME',
has_bias=True)
# deconv2_2 = _crop_and_concat(conv2_2, deconv2_1, (s_pool2, s_pool2), (s_pool3*2, s_pool3*2))
deconv2_2 = tf.concat(values=[conv2_2, deconv2_1], axis=-1)
deconv2_3 = _conv_layer(deconv2_2, [3, 3, 256, 128],
"deconv2_3",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
deconv2_4 = _conv_layer(deconv2_3, [3, 3, 128, 128],
"deconv2_4",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
deconv1_1 = _deconv_layer(deconv2_4, [2, 2, 64, 128],
_get_shape(deconv2_4),
'deconv1_1',
weight_decay, [1, 2, 2, 1],
pad='SAME',
has_bias=True)
# deconv1_2 = _crop_and_concat(conv1_2, deconv1_1, (s_pool2, s_pool2), (s_pool2, s_pool2))
deconv1_2 = tf.concat(values=[conv1_2, deconv1_1], axis=-1)
deconv1_3 = _conv_layer(deconv1_2, [3, 3, 128, 64],
"deconv1_2",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
deconv1_4 = _conv_layer(deconv1_3, [3, 3, 64, 64],
"deconv1_3",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
with tf.variable_scope('conv_classifier') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[1, 1, 64, num_classes],
ini=tf.contrib.layers.xavier_initializer_conv2d(dtype=tf.float32),
weight_decay=weight_decay)
biases = _variable_on_cpu('biases', [num_classes],
tf.constant_initializer(0.0))
conv = tf.nn.conv2d(deconv1_4, kernel, [1, 1, 1, 1], padding='SAME')
conv_classifier = tf.nn.bias_add(conv, biases, name=scope.name)
return conv_classifier
def unet(x, dropout, is_training, weight_decay, crop, num_input_bands,
num_classes, crop_size, extract_features):
x = tf.reshape(x, shape=[-1, crop, crop, num_input_bands])
conv1_1 = _conv_layer(x, [3, 3, num_input_bands, 64],
"conv1_1",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
conv1_2 = _conv_layer(conv1_1, [3, 3, 64, 64],
"conv1_2",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
s_pool1 = crop_size
pool1 = _max_pool(conv1_2, [1, 2, 2, 1], [1, 2, 2, 1], 'pool1', pad='SAME')
conv2_1 = _conv_layer(pool1, [3, 3, 64, 128],
"conv2_1",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
conv2_2 = _conv_layer(conv2_1, [3, 3, 128, 128],
"conv2_2",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
s_pool2 = math.ceil(s_pool1 / float(2))
# s_pool2 = math.ceil(float(s_pool1 - 2 + 1) / float(2))
pool2 = _max_pool(conv2_2, [1, 2, 2, 1], [1, 2, 2, 1], 'pool2', pad='SAME')
conv3_1 = _conv_layer(pool2, [3, 3, 128, 256],
"conv3_1",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
conv3_2 = _conv_layer(conv3_1, [3, 3, 256, 256],
"conv3_2",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
s_pool3 = math.ceil(s_pool2 / float(2))
# s_pool3 = math.ceil(float(s_pool2 - 2 + 1) / float(2))
print(s_pool1, s_pool2, s_pool3)
# pool3 = _max_pool(conv3_2, [1, 2, 2, 1], [1, 2, 2, 1], 'pool3', pad='SAME')
#
# conv4_1 = _conv_layer(pool2, [3, 3, 128, 256], "conv3_1", weight_decay, is_training,
# strides=[1, 1, 1, 1], pad='SAME')
# conv4_2 = _conv_layer(conv3_1, [3, 3, 256, 256], "conv3_2", weight_decay, is_training,
# strides=[1, 1, 1, 1], pad='SAME')
# ------------------------End of encoder-----------------------------
new_shape = [
tf.shape(conv3_2)[0],
tf.shape(conv3_2)[1] * 2,
tf.shape(conv3_2)[2] * 2,
tf.shape(conv3_2)[3] // 2
]
try:
output_shape = tf.pack(new_shape)
except:
output_shape = tf.stack(new_shape)
deconv2_1 = _deconv_layer(conv3_2, [2, 2, 128, 256],
output_shape,
'deconv2_1',
weight_decay, [1, 2, 2, 1],
pad='SAME',
has_bias=True)
# deconv2_2 = _crop_and_concat(conv2_2, deconv2_1, (s_pool2, s_pool2), (s_pool3*2, s_pool3*2))
deconv2_2 = tf.concat(values=[conv2_2, deconv2_1], axis=-1)
deconv2_3 = _conv_layer(deconv2_2, [3, 3, 256, 128],
"deconv2_3",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
deconv2_4 = _conv_layer(deconv2_3, [3, 3, 128, 128],
"deconv2_4",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
new_shape = [
tf.shape(deconv2_4)[0],
tf.shape(deconv2_4)[1] * 2,
tf.shape(deconv2_4)[2] * 2,
tf.shape(deconv2_4)[3] // 2
]
try:
output_shape = tf.pack(new_shape)
except:
output_shape = tf.stack(new_shape)
deconv1_1 = _deconv_layer(deconv2_4, [2, 2, 64, 128],
output_shape,
'deconv1_1',
weight_decay, [1, 2, 2, 1],
pad='SAME',
has_bias=True)
# deconv1_2 = _crop_and_concat(conv1_2, deconv1_1, (s_pool2, s_pool2), (s_pool2, s_pool2))
deconv1_2 = tf.concat(values=[conv1_2, deconv1_1], axis=-1)
deconv1_3 = _conv_layer(deconv1_2, [3, 3, 128, 64],
"deconv1_2",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
deconv1_4 = _conv_layer(deconv1_3, [3, 3, 64, 64],
"deconv1_3",
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME')
with tf.variable_scope('conv_classifier') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[1, 1, 64, num_classes],
ini=tf.contrib.layers.xavier_initializer_conv2d(dtype=tf.float32),
weight_decay=weight_decay)
biases = _variable_on_cpu('biases', [num_classes],
tf.constant_initializer(0.0))
conv = tf.nn.conv2d(deconv1_4, kernel, [1, 1, 1, 1], padding='SAME')
conv_classifier = tf.nn.bias_add(conv, biases, name=scope.name)
# resize to 32x32 or 64x64
# save only the first 64 maps
if extract_features is True:
return [tf.image.resize_bilinear(conv1_1, [32, 32]), 64], \
[tf.image.resize_bilinear(conv3_2, [32, 32]), 256], \
[tf.image.resize_bilinear(deconv1_4, [32, 32]), 64], conv_classifier
else:
return conv_classifier
def fcn_25_2_2x(x, dropout, is_training, crop_size, weight_decay,
num_input_bands, num_classes, extract_features):
# Reshape input picture
x = tf.reshape(x, shape=[-1, crop_size, crop_size, num_input_bands])
# print x.get_shape()
conv1_1 = _conv_layer(x, [3, 3, num_input_bands, 64],
'conv1_1',
weight_decay,
is_training,
batch_norm=True)
conv1_2 = _conv_layer(conv1_1, [3, 3, 64, 64],
'conv1_2',
weight_decay,
is_training,
batch_norm=True)
pool1 = _max_pool(conv1_2,
kernel=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
name='pool_1')
conv2_1 = _conv_layer(pool1, [3, 3, 64, 128],
'conv2_1',
weight_decay,
is_training,
batch_norm=True)
conv2_2 = _conv_layer(conv2_1, [3, 3, 128, 128],
'conv2_2',
weight_decay,
is_training,
batch_norm=True)
pool2 = _max_pool(conv2_2,
kernel=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
name='pool_2')
# reshape = tf.reshape(pool3, [-1, 7*7*256])
# fc1 = _fc_layer(pool2, layerShape=[3, 3, 128, 1024], name='fc1', weight_decay=weight_decay)
fc1 = _conv_layer(pool2,
layer_shape=[3, 3, 128, 1024],
name='fc1',
weight_decay=weight_decay,
is_training=is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='relu',
batch_norm=False,
has_activation=True)
drop_fc1 = tf.nn.dropout(fc1, dropout)
# fc2 = _fc_layer(drop_fc1, layerShape=[1, 1, 1024, 1024], name='fc2', weight_decay=weight_decay)
fc2 = _conv_layer(drop_fc1,
layer_shape=[1, 1, 1024, 1024],
name='fc2',
weight_decay=weight_decay,
is_training=is_training,
strides=[1, 1, 1, 1],
pad='SAME',
activation='relu',
batch_norm=False,
has_activation=True)
drop_fc2 = tf.nn.dropout(fc2, dropout)
# score_fr = _score_layer(drop_fc2, 'score_fr', weight_decay)
score_fr = _conv_layer(
drop_fc2, [1, 1, drop_fc2.get_shape()[3].value, num_classes],
'score_fr',
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
batch_norm=False,
has_activation=False)
new_shape = [
tf.shape(pool1)[0],
tf.shape(pool1)[1],
tf.shape(pool1)[2], num_classes
]
try:
output_shape = tf.pack(new_shape)
except:
output_shape = tf.stack(new_shape)
# upscore2 = _upscore_layer(score_fr, layerShape=tf.shape(pool1), name='upscore2',
# weight_decay=weight_decay, ksize=4, stride=2)
upscore2 = _deconv_layer(
score_fr,
[4, 4, num_classes, score_fr.get_shape()[3].value],
output_shape,
'upscore2',
weight_decay,
strides=[1, 2, 2, 1],
pad='SAME')
# score_pool4 = _score_layer(pool1, "score_pool1", weight_decay)
score_pool4 = _conv_layer(
pool1, [1, 1, pool1.get_shape()[3].value, num_classes],
'score_pool1',
weight_decay,
is_training,
strides=[1, 1, 1, 1],
pad='SAME',
batch_norm=False,
has_activation=False)
fuse_pool4 = tf.add(upscore2, score_pool4)
new_shape = [tf.shape(x)[0], tf.shape(x)[1], tf.shape(x)[2], num_classes]
try:
output_shape = tf.pack(new_shape)
except:
output_shape = tf.stack(new_shape)
# upscore3 = _upscore_layer(fuse_pool4, layerShape=tf.shape(x), name='upscore3', weight_decay=weight_decay,
# ksize=4, stride=2)
upscore3 = _deconv_layer(
fuse_pool4,
[4, 4, num_classes, fuse_pool4.get_shape()[3].value],
output_shape,
'upscore3',
weight_decay,
strides=[1, 2, 2, 1],
pad='SAME')
return upscore3
