一、TensorFlow運作方式入門
fully_connected_feed.py
# Copyright 2015 Google Inc. 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.
# ==============================================================================
"""Trains and Evaluates the MNIST network using a feed dictionary."""
# pylint: disable=missing-docstring
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os.path
import time
import tensorflow.python.platform
import numpy
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
#from tensorflow.examples.tutorials.mnist import input_data
#from tensorflow.examples.tutorials.mnist import mnist
import input_data, mnist
# Basic model parameters as external flags.
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
flags.DEFINE_integer('max_steps', 2000, 'Number of steps to run trainer.')
flags.DEFINE_integer('hidden1', 128, 'Number of units in hidden layer 1.')
flags.DEFINE_integer('hidden2', 32, 'Number of units in hidden layer 2.')
flags.DEFINE_integer('batch_size', 100, 'Batch size. '
'Must divide evenly into the dataset sizes.')
flags.DEFINE_string('train_dir', 'Mnist_data/', 'Directory to put the training data.')
flags.DEFINE_boolean('fake_data', False, 'If true, uses fake data '
'for unit testing.')
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_PIXELS))
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().
"""
# 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 run_training():
"""Train MNIST for a number of steps."""
# Get the sets of images and labels for training, validation, and
# test on MNIST.
data_sets = input_data.read_data_sets(FLAGS.train_dir, FLAGS.fake_data)
# Tell TensorFlow that the model will be built into the default Graph.
with tf.Graph().as_default():
# Generate placeholders for the images and labels.
images_placeholder, labels_placeholder = placeholder_inputs(
FLAGS.batch_size)
# Build a Graph that computes predictions from the inference model.
logits = mnist.inference(images_placeholder,
FLAGS.hidden1,
FLAGS.hidden2)
# Add to the Graph the Ops for loss calculation.
loss = mnist.loss(logits, labels_placeholder)
# Add to the Graph the Ops that calculate and apply gradients.
train_op = mnist.training(loss, FLAGS.learning_rate)
# Add the Op to compare the logits to the labels during evaluation.
eval_correct = mnist.evaluation(logits, labels_placeholder)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Create a saver for writing training checkpoints.
saver = tf.train.Saver()
# Create a session for running Ops on the Graph.
sess = tf.Session()
# Run the Op to initialize the variables.
init = tf.initialize_all_variables()
sess.run(init)
# Instantiate a SummaryWriter to output summaries and the Graph.
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir,
graph_def=sess.graph_def)
# And then after everything is built, start the training loop.
for step in xrange(FLAGS.max_steps):
start_time = time.time()
# Fill a feed dictionary with the actual set of images and labels
# for this particular training step.
feed_dict = fill_feed_dict(data_sets.train,
images_placeholder,
labels_placeholder)
# Run one step of the model. The return values are the activations
# from the `train_op` (which is discarded) and the `loss` Op. To
# inspect the values of your Ops or variables, you may include them
# in the list passed to sess.run() and the value tensors will be
# returned in the tuple from the call.
_, loss_value = sess.run([train_op, loss],
feed_dict=feed_dict)
duration = time.time() - start_time
# Write the summaries and print an overview fairly often.
if step % 100 == 0:
# Print status to stdout.
print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value, duration))
# Update the events file.
summary_str = sess.run(summary_op, feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
# Save a checkpoint and evaluate the model periodically.
if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps:
saver.save(sess, FLAGS.train_dir, 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)
def main(_):
run_training()
if __name__ == '__main__':
tf.app.run()
**`fully_connected_feed.py`**的運行結果如下（本人電腦爲2 CPU，沒有使用GPU）：
```
Extracting Mnist_data/train-images-idx3-ubyte.gz
Extracting Mnist_data/train-labels-idx1-ubyte.gz
Extracting Mnist_data/t10k-images-idx3-ubyte.gz
Extracting Mnist_data/t10k-labels-idx1-ubyte.gz
I tensorflow/core/common_runtime/local_device.cc:25] Local device intra op parallelism threads: 2
I tensorflow/core/common_runtime/local_session.cc:45] Local session inter op parallelism threads: 2
Step 0: loss = 2.33 (0.023 sec)
Step 100: loss = 2.09 (0.007 sec)
Step 200: loss = 1.76 (0.009 sec)
Step 300: loss = 1.36 (0.007 sec)
Step 400: loss = 1.12 (0.007 sec)
Step 500: loss = 0.74 (0.008 sec)
Step 600: loss = 0.78 (0.006 sec)
Step 700: loss = 0.69 (0.007 sec)
Step 800: loss = 0.67 (0.007 sec)
Step 900: loss = 0.52 (0.010 sec)
Training Data Eval:
Num examples: 55000 Num correct: 47532 Precision @ 1: 0.8642
Validation Data Eval:
Num examples: 5000 Num correct: 4360 Precision @ 1: 0.8720
Test Data Eval:
Num examples: 10000 Num correct: 8705 Precision @ 1: 0.8705
Step 1000: loss = 0.56 (0.013 sec)
Step 1100: loss = 0.50 (0.145 sec)
Step 1200: loss = 0.33 (0.007 sec)
Step 1300: loss = 0.44 (0.006 sec)
Step 1400: loss = 0.39 (0.006 sec)
Step 1500: loss = 0.33 (0.009 sec)
Step 1600: loss = 0.56 (0.008 sec)
Step 1700: loss = 0.50 (0.007 sec)
Step 1800: loss = 0.42 (0.006 sec)
Step 1900: loss = 0.41 (0.006 sec)
Training Data Eval:
Num examples: 55000 Num correct: 49220 Precision @ 1: 0.8949
Validation Data Eval:
Num examples: 5000 Num correct: 4520 Precision @ 1: 0.9040
Test Data Eval:
Num examples: 10000 Num correct: 9014 Precision @ 1: 0.9014
[Finished in 22.8s]
二、 Tensorboard訓練過程可視化
mnist_with_summaries.py
# Copyright 2015 Google Inc. 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 very simple MNIST classifier, modified to display data in TensorBoard.
See extensive documentation for the original model at
http://tensorflow.org/tutorials/mnist/beginners/index.md
See documentation on the TensorBoard specific pieces at
http://tensorflow.org/how_tos/summaries_and_tensorboard/index.md
If you modify this file, please update the exerpt in
how_tos/summaries_and_tensorboard/index.md.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow.python.platform
#from tensorflow.examples.tutorials.mnist import input_data
import input_data
import tensorflow as tf
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_boolean('fake_data', False, 'If true, uses fake data '
'for unit testing.')
flags.DEFINE_integer('max_steps', 1000, 'Number of steps to run trainer.')
flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
def main(_):
# Import data
mnist = input_data.read_data_sets('Mnist_data/', one_hot=True,
fake_data=FLAGS.fake_data)
sess = tf.InteractiveSession()
# Create the model
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
W = tf.Variable(tf.zeros([784, 10]), name='weights')
b = tf.Variable(tf.zeros([10], name='bias'))
# Use a name scope to organize nodes in the graph visualizer
with tf.name_scope('Wx_b'):
y = tf.nn.softmax(tf.matmul(x, W) + b)
# Add summary ops to collect data
_ = tf.histogram_summary('weights', W)
_ = tf.histogram_summary('biases', b)
_ = tf.histogram_summary('y', y)
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')
# More name scopes will clean up the graph representation
with tf.name_scope('xent'):
cross_entropy = -tf.reduce_sum(y_ * tf.log(y))
_ = tf.scalar_summary('cross entropy', cross_entropy)
with tf.name_scope('train'):
train_step = tf.train.GradientDescentOptimizer(
FLAGS.learning_rate).minimize(cross_entropy)
with tf.name_scope('test'):
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
_ = tf.scalar_summary('accuracy', accuracy)
# Merge all the summaries and write them out to /tmp/mnist_logs
merged = tf.merge_all_summaries()
writer = tf.train.SummaryWriter('/tmp/mnist_logs', sess.graph_def)
tf.initialize_all_variables().run()
# Train the model, and feed in test data and record summaries every 10 steps
for i in range(FLAGS.max_steps):
if i % 10 == 0: # Record summary data and the accuracy
if FLAGS.fake_data:
batch_xs, batch_ys = mnist.train.next_batch(
100, fake_data=FLAGS.fake_data)
feed = {x: batch_xs, y_: batch_ys}
else:
feed = {x: mnist.test.images, y_: mnist.test.labels}
result = sess.run([merged, accuracy], feed_dict=feed)
summary_str = result[0]
acc = result[1]
writer.add_summary(summary_str, i)
print('Accuracy at step %s: %s' % (i, acc))
else:
batch_xs, batch_ys = mnist.train.next_batch(
100, fake_data=FLAGS.fake_data)
feed = {x: batch_xs, y_: batch_ys}
sess.run(train_step, feed_dict=feed)
if __name__ == '__main__':
tf.app.run()
**`mnist_with_summaries.py`**主要提供了一種在Tensorboard可視化方法，首先，編譯運行代碼：
運行完畢後，打開終端`Terminal`，輸入`tensorboard --logdir=/tmp/mnist_logs`，就會運行出：`Starting TensorBoard on port 6006 (You can navigate to http://localhost:6006)`
然後，打開瀏覽器，輸入鏈接`http://localhost:6006`：
其中，有一些選項，例如菜單欄裏包括`EVENTS, IMAGES, GRAPH, HISTOGRAMS`，都可以一一點開查看~
另外，此時如果不關閉該終端，是無法在其他終端中重新生成可視化結果的，會出現端口占用的錯誤。
