-
Notifications
You must be signed in to change notification settings - Fork 1
/
train.py
215 lines (169 loc) · 7.69 KB
/
train.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
205
206
207
208
209
210
211
212
213
214
215
"""
Train mnist
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import os.path
import time
import numpy as np
import tensorflow as tf
import partnet
import mnist
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('train_dir', './cifar10_train',
"""Directory where to write event logs """
"""and checkpoint.""")
tf.app.flags.DEFINE_integer('max_steps', 1000000,
"""Number of batches to run.""")
tf.app.flags.DEFINE_integer('batch_size', 128,
"""Number of images to process in a batch.""")
tf.app.flags.DEFINE_string('data_dir', './cifar10_data',
"""Path to the CIFAR-10 data directory.""")
tf.app.flags.DEFINE_bool('fake_data', False,
"""Whether use fake data.""")
def placeholder_inputs(batch_size):
"""Generate placeholder variables to represent the input tensors.
These placeholders are used as inputs by the rest of the model building
code and will be fed from the downloaded data in the .run() loop, below.
Args:
batch_size: The batch size will be baked into both placeholders.
Returns:
images_placeholder: Images placeholder.
labels_placeholder: Labels placeholder.
"""
# Note that the shapes of the placeholders match the shapes of the full
# image and label tensors, except the first dimension is now batch_size
# rather than the full size of the train or test data sets.
images_placeholder = tf.placeholder(tf.float32,
shape=(batch_size, mnist.IMAGE_SIZE,
mnist.IMAGE_SIZE, 1))
labels_placeholder = tf.placeholder(tf.int32, shape=(batch_size,))
return images_placeholder, labels_placeholder
def fill_feed_dict(data_set, images_pl, labels_pl):
"""Fills the feed_dict for training the given step.
A feed_dict takes the form of:
feed_dict = {
<placeholder>: <tensor of values to be passed for placeholder>,
....
}
Args:
data_set: The set of images and labels, from input_data.read_data_sets()
images_pl: The images placeholder, from placeholder_inputs().
labels_pl: The labels placeholder, from placeholder_inputs().
Returns:
feed_dict: The feed dictionary mapping from placeholders to values.
"""
# Create the feed_dict for the placeholders filled with the next
# `batch size` examples.
images_feed, labels_feed = data_set.next_batch(FLAGS.batch_size,
FLAGS.fake_data)
feed_dict = {
images_pl: images_feed,
labels_pl: labels_feed,
}
return feed_dict
def do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_set):
"""Runs one evaluation against the full epoch of data.
Args:
sess: The session in which the model has been trained.
eval_correct: The Tensor that returns the number of correct predictions.
images_placeholder: The images placeholder.
labels_placeholder: The labels placeholder.
data_set: The set of images and labels to evaluate, from
input_data.read_data_sets().
eval all the data in the dataset
"""
# And run one epoch of eval.
true_count = 0 # Counts the number of correct predictions.
steps_per_epoch = data_set.num_examples // FLAGS.batch_size
num_examples = steps_per_epoch * FLAGS.batch_size
for step in xrange(steps_per_epoch):
feed_dict = fill_feed_dict(data_set,
images_placeholder,
labels_placeholder)
true_count += sess.run(eval_correct, feed_dict=feed_dict)
precision = true_count / num_examples
print(' Num examples: %d Num correct: %d Precision @ 1: %0.04f' %
(num_examples, true_count, precision))
def train():
"""Train CIFAR-10 for a number of steps."""
data_sets = mnist.read_mnist(FLAGS.data_dir, FLAGS.fake_data)
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
images_placeholder, labels_placeholder = placeholder_inputs(
FLAGS.batch_size)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = partnet.inference(images_placeholder, is_training=True)
# Calculate loss.
loss = partnet.loss(logits, labels_placeholder, sparse_weight=0.01)
# Add the Op to compare the logits to the labels during evaluation.
eval_correct = partnet.evaluation(logits, labels_placeholder)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = partnet.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session()
sess.run(init)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
for step in xrange(FLAGS.max_steps):
start_time = time.time()
feed_dict = fill_feed_dict(data_sets.train,
images_placeholder,
labels_placeholder)
_, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 100 == 0:
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print(format_str % (datetime.now(), step, loss_value,
examples_per_sec, sec_per_batch))
summary_str = sess.run(summary_op, feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
# Save the model checkpoint periodically.
if step % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
# Evaluate against the training set.
print('Training Data Eval:')
do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_sets.train)
# Evaluate against the validation set.
print('Validation Data Eval:')
do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_sets.validation)
# Evaluate against the test set.
print('Test Data Eval:')
do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_sets.test)
sess.close() # free resource
def main(argv=None): # pylint: disable=unused-argument
train()
if __name__ == '__main__':
tf.app.run()