-
Notifications
You must be signed in to change notification settings - Fork 0
/
fully_convnets_potsdam.py
204 lines (161 loc) · 8.52 KB
/
fully_convnets_potsdam.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
from __future__ import division
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import xrange
import tensor_utils_5_channels as utils
FLAGS = tf.flags.FLAGS
tf.flags.DEFINE_integer("batch_size", "12", "batch size for training")
tf.flags.DEFINE_string("logs_dir", "../logs-vgg19/", "path to logs directory")
tf.flags.DEFINE_float("learning_rate", "1e-4", "Learning rate for Adam Optimizer")
tf.flags.DEFINE_string("model_dir", "ISPRS_semantic_labeling_Potsdam/imagenet-vgg-verydeep-19.mat",
"Path to vgg model mat")
tf.flags.DEFINE_bool('debug', "False", "Debug mode: True/ False")
tf.flags.DEFINE_string('mode', "train", "Mode train/ test/ visualize")
MODEL_URL = 'http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat'
MAX_ITERATION = int(1e7 + 1)
NUM_OF_CLASSESS = 6
IMAGE_SIZE = 224
tf_records_filename = 'Potsdam.tfrecords'
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':
append_channels= np.random.normal(loc=0,scale=0.02,size=(3,3,3,64))
kernels = np.concatenate((kernels, append_channels), axis=2)
kernels = utils.get_variable(np.transpose(kernels, (0, 1, 2, 3)), name=name + "_w")
else:
kernels = utils.get_variable(np.transpose(kernels, (0, 1, 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(image, keep_prob):
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, [97.6398951221, 45.548982716, 31.4374])
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")
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)
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 train(loss_val, var_list):
optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate)
grads = optimizer.compute_gradients(loss_val, var_list=var_list)
return optimizer.apply_gradients(grads)
def read_and_decode(filename_queue):
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
features={
'image_raw': tf.FixedLenFeature([], tf.string),
'annotation_raw': tf.FixedLenFeature([], tf.string)
})
image = tf.decode_raw(features['image_raw'], tf.float16)
annotation = tf.decode_raw(features['annotation_raw'], tf.uint8)
image = tf.reshape(image, [224, 224, 6])
annotation = tf.reshape(annotation, [224, 224, 1])
min_after_deque = 1000
batch_size = 12
num_thread = 20
capacity = min_after_deque + (num_thread + 1) * batch_size
images, annotations = tf.train.shuffle_batch([image, annotation], batch_size=batch_size, num_threads=num_thread,
min_after_dequeue=min_after_deque, capacity=capacity)
return images, annotations
def main(argv=None):
filename_queue = tf.train.string_input_producer([tf_records_filename])
image, annotation = read_and_decode(filename_queue)
image = tf.cast(image, dtype=tf.float32)
annotation = tf.cast(annotation, dtype=tf.int32)
keep_probability = tf.placeholder(tf.float32, name="keep_probabilty")
pred_annotation, logits = inference(image, keep_probability)
annotation_64 = tf.cast(annotation, dtype=tf.int64)
# calculate accuracy for batch.
cal_acc = tf.equal(pred_annotation, annotation_64)
cal_acc = tf.cast(cal_acc, dtype=tf.int8)
acc = tf.count_nonzero(cal_acc) / (FLAGS.batch_size * IMAGE_SIZE * IMAGE_SIZE)
loss = tf.reduce_mean((tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits,
labels=tf.squeeze(annotation,
squeeze_dims=[3]),
name="entropy")))
loss_summary=tf.summary.scalar("entropy", loss)
acc_summary=tf.summary.scalar("accuracy", acc)
trainable_var = tf.trainable_variables()
train_op = train(loss, trainable_var)
sess = tf.Session()
print("Setting up Saver...")
saver = tf.train.Saver()
train_writer = tf.summary.FileWriter(FLAGS.logs_dir + '/train', sess.graph)
sess.run(tf.global_variables_initializer())
ckpt = tf.train.get_checkpoint_state(FLAGS.logs_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
print("Model restored...")
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord,sess=sess)
for itr in xrange(MAX_ITERATION):
feed_dict = {keep_probability: 0.75}
sess.run(train_op, feed_dict=feed_dict)
if itr % 50 == 0:
train_loss, train_acc, summary_loss, summary_acc = sess.run([loss, acc, loss_summary, acc_summary], feed_dict=feed_dict)
print("Step: %d, Train_loss: %g, Train_acc: %g" % (itr, train_loss, train_acc))
train_writer.add_summary(summary_loss, itr)
train_writer.add_summary(summary_acc, itr)
if itr % 500 == 0:
saver.save(sess, FLAGS.logs_dir + "model.ckpt", itr)
coord.request_stop()
coord.join(threads)
if __name__ == "__main__":
tf.app.run()