-
Notifications
You must be signed in to change notification settings - Fork 674
/
mnist_with_summaries.py
227 lines (201 loc) · 8.94 KB
/
mnist_with_summaries.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
216
217
218
219
220
221
222
223
224
225
226
227
# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the 'License');
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an 'AS IS' BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""A simple MNIST classifier which displays summaries in TensorBoard.
This is an unimpressive MNIST model, but it is a good example of using
tf.name_scope to make a graph legible in the TensorBoard graph explorer, and of
naming summary tags so that they are grouped meaningfully in TensorBoard.
It demonstrates the functionality of every TensorBoard dashboard.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import os
import sys
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
FLAGS = None
def train():
# Import data
mnist = input_data.read_data_sets(FLAGS.data_dir, fake_data=FLAGS.fake_data)
sess = tf.InteractiveSession()
# Create a multilayer model.
# Input placeholders
with tf.name_scope("input"):
x = tf.placeholder(tf.float32, [None, 784], name="x-input")
y_ = tf.placeholder(tf.int64, [None], name="y-input")
with tf.name_scope("input_reshape"):
image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
tf.summary.image("input", image_shaped_input, 10)
# We can't initialize these variables to 0 - the network will get stuck.
def weight_variable(shape):
"""Create a weight variable with appropriate initialization."""
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
"""Create a bias variable with appropriate initialization."""
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def variable_summaries(var):
"""Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
with tf.name_scope("summaries"):
mean = tf.reduce_mean(var)
tf.summary.scalar("mean", mean)
with tf.name_scope("stddev"):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.summary.scalar("stddev", stddev)
tf.summary.scalar("max", tf.reduce_max(var))
tf.summary.scalar("min", tf.reduce_min(var))
tf.summary.histogram("histogram", var)
def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
"""Reusable code for making a simple neural net layer.
It does a matrix multiply, bias add, and then uses ReLU to nonlinearize.
It also sets up name scoping so that the resultant graph is easy to read,
and adds a number of summary ops.
"""
# Adding a name scope ensures logical grouping of the layers in the graph.
with tf.name_scope(layer_name):
# This Variable will hold the state of the weights for the layer
with tf.name_scope("weights"):
weights = weight_variable([input_dim, output_dim])
variable_summaries(weights)
with tf.name_scope("biases"):
biases = bias_variable([output_dim])
variable_summaries(biases)
with tf.name_scope("Wx_plus_b"):
preactivate = tf.matmul(input_tensor, weights) + biases
tf.summary.histogram("pre_activations", preactivate)
activations = act(preactivate, name="activation")
tf.summary.histogram("activations", activations)
return activations
hidden1 = nn_layer(x, 784, 500, "layer1")
with tf.name_scope("dropout"):
keep_prob = tf.placeholder(tf.float32)
tf.summary.scalar("dropout_keep_probability", keep_prob)
dropped = tf.nn.dropout(hidden1, keep_prob)
# Do not apply softmax activation yet, see below.
y = nn_layer(dropped, 500, 10, "layer2", act=tf.identity)
with tf.name_scope("cross_entropy"):
# The raw formulation of cross-entropy,
#
# tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.softmax(y)),
# reduction_indices=[1]))
#
# can be numerically unstable.
#
# So here we use tf.losses.sparse_softmax_cross_entropy on the
# raw logit outputs of the nn_layer above, and then average across
# the batch.
with tf.name_scope("total"):
cross_entropy = tf.losses.sparse_softmax_cross_entropy(labels=y_, logits=y)
tf.summary.scalar("cross_entropy", cross_entropy)
with tf.name_scope("train"):
train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(cross_entropy)
with tf.name_scope("accuracy"):
with tf.name_scope("correct_prediction"):
correct_prediction = tf.equal(tf.argmax(y, 1), y_)
with tf.name_scope("accuracy"):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar("accuracy", accuracy)
# Merge all the summaries and write them out to
# /tmp/tensorflow/mnist/logs/mnist_with_summaries (by default)
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(FLAGS.log_dir + "/train", sess.graph)
test_writer = tf.summary.FileWriter(FLAGS.log_dir + "/test")
tf.global_variables_initializer().run()
# Train the model, and also write summaries.
# Every 10th step, measure test-set accuracy, and write test summaries
# All other steps, run train_step on training data, & add training summaries
def feed_dict(train): # pylint: disable=redefined-outer-name
"""Make a TensorFlow feed_dict: maps data onto Tensor placeholders."""
if train or FLAGS.fake_data:
xs, ys = mnist.train.next_batch(FLAGS.batch_size, fake_data=FLAGS.fake_data)
k = FLAGS.dropout
else:
xs, ys = mnist.test.images, mnist.test.labels
k = 1.0
return {x: xs, y_: ys, keep_prob: k}
for i in range(FLAGS.max_steps):
if i % 10 == 0: # Record summaries and test-set accuracy
summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
test_writer.add_summary(summary, i)
print("Accuracy at step %s: %s" % (i, acc))
else: # Record train set summaries, and train
if i % 100 == 99: # Record execution stats
run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
summary, _ = sess.run(
[merged, train_step],
feed_dict=feed_dict(True),
options=run_options,
run_metadata=run_metadata,
)
train_writer.add_run_metadata(run_metadata, "step%03d" % i)
train_writer.add_summary(summary, i)
print("Adding run metadata for", i)
else: # Record a summary
summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
train_writer.add_summary(summary, i)
train_writer.close()
test_writer.close()
def main(_):
if tf.gfile.Exists(FLAGS.log_dir):
tf.gfile.DeleteRecursively(FLAGS.log_dir)
tf.gfile.MakeDirs(FLAGS.log_dir)
train()
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--fake_data",
nargs="?",
const=True,
type=bool,
default=False,
help="If true, uses fake data for unit testing.",
)
parser.add_argument(
"--max_steps", type=int, default=1000, help="Number of steps to run trainer."
)
parser.add_argument(
"--learning_rate", type=float, default=0.001, help="Initial learning rate"
)
parser.add_argument(
"--batch_size", type=int, default=100, help="Training batch size"
)
parser.add_argument(
"--dropout",
type=float,
default=0.9,
help="Keep probability for training dropout.",
)
parser.add_argument(
"--data_dir",
type=str,
default=os.path.join(
os.getenv("TEST_TMPDIR", "/tmp"), "tensorflow/mnist/input_data"
),
help="Directory for storing input data",
)
parser.add_argument(
"--log_dir",
type=str,
default=os.path.join(
os.getenv("TEST_TMPDIR", "/tmp"),
"tensorflow/mnist/logs/mnist_with_summaries",
),
help="Summaries log directory",
)
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)