full_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
# Basic model parameters as external flags.
#类似于C里面的define
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', '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.
#https://zhuanlan.zhihu.com/p/25307881
#tf.Variable适合一些需要初始化或被训练而变化的权重或参数，而tf.placeholder适合通常不会改变的被训练的数据集。
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.
#================================================================
#在这里每一步都取到了固定的 FLAGS.batch_size
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
#＊_placeholder提供了训练好的网络的接口
#data_set是不同的数据集（训练集、测试集、验证集）
#eval_correct是集合数据验证正确的个数总和
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.
#1个epoch等于使用训练集中的全部样本训练一次；1个iteration等于使用batchsize个样本训练一次
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.
#获取这一步用于训练的batch数据
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.
#按照给定的数据训练（feed_dict）、给定的训练方法（train_op），训练一次网络
#顺便获得训练之前损失函数的值（注：train_op没有输出，所以是“_”）
_, 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.
# 然后把图表运行的信息写到缓冲区，更新磁盘文件
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()
mnist.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.
# ==============================================================================
"""Builds the MNIST network.
Implements the inference/loss/training pattern for model building.
1. inference() - Builds the model as far as is required for running the network
forward to make predictions.
2. loss() - Adds to the inference model the layers required to generate loss.
3. training() - Adds to the loss model the Ops required to generate and
apply gradients.
This file is used by the various "fully_connected_*.py" files and not meant to
be run.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import tensorflow.python.platform
import tensorflow as tf
# The MNIST dataset has 10 classes, representing the digits 0 through 9.
NUM_CLASSES = 10
# The MNIST images are always 28x28 pixels.
IMAGE_SIZE = 28
IMAGE_PIXELS = IMAGE_SIZE * IMAGE_SIZE
def inference(images, hidden1_units, hidden2_units):
"""Build the MNIST model up to where it may be used for inference.
Args:
images: Images placeholder, from inputs().
hidden1_units: Size of the first hidden layer.
hidden2_units: Size of the second hidden layer.
Returns:
softmax_linear: Output tensor with the computed logits.
"""
# Hidden 1
with tf.name_scope('hidden1'):
weights = tf.Variable(
tf.truncated_normal([IMAGE_PIXELS, hidden1_units],
stddev=1.0 / math.sqrt(float(IMAGE_PIXELS))),
name='weights')
biases = tf.Variable(tf.zeros([hidden1_units]),
name='biases')
hidden1 = tf.nn.relu(tf.matmul(images, weights) + biases)
# Hidden 2
with tf.name_scope('hidden2'):
weights = tf.Variable(
tf.truncated_normal([hidden1_units, hidden2_units],
stddev=1.0 / math.sqrt(float(hidden1_units))),
name='weights')
biases = tf.Variable(tf.zeros([hidden2_units]),
name='biases')
hidden2 = tf.nn.relu(tf.matmul(hidden1, weights) + biases)
# Linear
with tf.name_scope('softmax_linear'):
weights = tf.Variable(
tf.truncated_normal([hidden2_units, NUM_CLASSES],
stddev=1.0 / math.sqrt(float(hidden2_units))),
name='weights')
biases = tf.Variable(tf.zeros([NUM_CLASSES]),
name='biases')
logits = tf.matmul(hidden2, weights) + biases
return logits
def loss(logits, labels):
"""Calculates the loss from the logits and the labels.
Args:
logits: Logits tensor, float - [batch_size, NUM_CLASSES].
labels: Labels tensor, int32 - [batch_size].
Returns:
loss: Loss tensor of type float """
# Convert from sparse integer labels in the range [0, NUM_CLASSES)
# to 1-hot dense float vectors (that is we will have batch_size vectors,
# each with NUM_CLASSES values, all of which are 0.0 except there will
# be a 1.0 in the entry corresponding to the label).
'''
t1 = [[1,2,3], [4,5,6]]
t2 = [[7,8,9], [10,11,12]]
tf.concat(0, [t1, t2]) ==> [[1,2,3], [4,5,6], [7,8,9], [10,11,12]]
tf.concat(1, [t1, t2]) ==> [[1,2,3,7,8, 9], [4,5,6,10,11, 12]]
'''
batch_size = tf.size(labels)
# 为什么需要在这里增加一维？
labels = tf.expand_dims(labels, 1)
indices = tf.expand_dims(tf.range(0, batch_size), 1)
# 具体是什么意义？ 为何要拼接在一起？
concated = tf.concat(1, [indices, labels])
# tf.sparse_to_dense http://blog.youkuaiyun.com/mao_xiao_feng/article/details/53365889
onehot_labels = tf.sparse_to_dense(
concated, tf.pack([batch_size, NUM_CLASSES]), 1.0, 0.0)
'''
将一系列rank-R的tensor打包为一个rank-(R+1)的tensor
# ‘x’ is [1, 4], ‘y’ is [2, 5], ‘z’ is [3, 6]
pack([x, y, z]) => [[1, 4], [2, 5], [3, 6]]
# 沿着第一维pack
pack([x, y, z], axis=1) => [[1, 2, 3], [4, 5, 6]]
等价于tf.pack([x, y, z]) = np.asarray([x, y, z])
'''
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits,
onehot_labels,
name='xentropy')
loss = tf.reduce_mean(cross_entropy, name='xentropy_mean')
return loss
def training(loss, learning_rate):
"""Sets up the training Ops.
Creates a summarizer to track the loss over time in TensorBoard.
Creates an optimizer and applies the gradients to all trainable variables.
The Op returned by this function is what must be passed to the
`sess.run()` call to cause the model to train.
Args:
loss: Loss tensor, from loss().
learning_rate: The learning rate to use for gradient descent.
Returns:
train_op: The Op for training.
"""
# Add a scalar summary for the snapshot loss.
tf.scalar_summary(loss.op.name, loss)
# Create the gradient descent optimizer with the given learning rate.
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
# Create a variable to track the global step.
global_step = tf.Variable(0, name='global_step', trainable=False)
# Use the optimizer to apply the gradients that minimize the loss
# (and also increment the global step counter) as a single training step.
train_op = optimizer.minimize(loss, global_step=global_step)
return train_op
def evaluation(logits, labels):
"""Evaluate the quality of the logits at predicting the label.
Args:
logits: Logits tensor, float - [batch_size, NUM_CLASSES].
labels: Labels tensor, int32 - [batch_size], with values in the
range [0, NUM_CLASSES).
Returns:
A scalar int32 tensor with the number of examples (out of batch_size)
that were predicted correctly.
"""
# For a classifier model, we can use the in_top_k Op.
# It returns a bool tensor with shape [batch_size] that is true for
# the examples where the label's is was in the top k (here k=1)
# of all logits for that example.
correct = tf.nn.in_top_k(logits, labels, 1)
# Return the number of true entries.
return tf.reduce_sum(tf.cast(correct, tf.int32))
根据tensorflow的版本的变更，有的函数需要改变一下名字，例如
tf.merge_all_summaries() 需要改变为 tf.summary.merge_all()
tf.train.SummaryWriter()需要改为 tf.summary.FileWriter() 等
扫一扫
2256
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
