mnist.py文件
# coding=utf-8
'''
Created on Feb 11, 2019
@author: zhongzhu
'''
# 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.
# ==============================================================================
"""Builds the MNIST network.
Implements the inference/loss/training pattern for model building.
1. inference() - Builds the model as far as 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.
"""
import math
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.
"""
labels = tf.to_int64(labels)
return tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
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.
"""
with tf.name_scope('scalar_summaries'):
# Add a scalar summary for the snapshot loss.
tf.summary.scalar('loss', loss)
tf.summary.scalar('learning_rate', learning_rate)
# 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 is 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))
fully_connected_toturol.py文件
# coding=utf-8
'''
Created on Feb 11, 2019
@author: zhongzhu
'''
import argparse
import os.path
import sys
import time
import os
from six.moves import xrange
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# from tensorflow.examples.tutorials.mnist import mnist
import mnist
#过滤警告信息
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
# 全局变量，用来存放基本的模型(超)参数.
FLAGS = None
#产生 placeholder variables来表达输入张量
def placeholder_inputs(batch_size):
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):
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
#在给定的数据集上执行一次评估操作
def do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_set):
true_count = 0
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 = float(true_count) / num_examples
print(' Num examples: %d Num correct: %d Precision @ 1: %0.04f' %
(num_examples, true_count, precision))
# 启动训练过程
def run_training():
data_sets = input_data.read_data_sets(FLAGS.input_data_dir, FLAGS.fake_data)
# 告诉Tensorflow模型将会被构建在默认的Graph上
with tf.Graph().as_default():
images_placeholder, labels_placeholder = placeholder_inputs(FLAGS.batch_size)
#从前向推断模型中构建用于预测的计算图
logits = mnist.inference(images_placeholder, FLAGS.hidden1, FLAGS.hidden2)
#为计算图添加计算损失的节点
loss = mnist.loss(logits, labels_placeholder)
#为计算图添加计算和应用梯度的节点
train_op = mnist.training(loss, FLAGS.learning_rate)
# 添加评估节点
eval_correct = mnist.evaluation(logits, labels_placeholder)
init = tf.global_variables_initializer()
merged_summaries = tf.summary.merge_all()
saver = tf.train.Saver()
# 创建一个会话用来运行计算图中的节点
sess = tf.Session()
# 实例化一个 SummaryWriter 输出 summaries 和 Graph.
summary_writer = tf.summary.FileWriter(FLAGS.log_dir, sess.graph)
summary_writer.flush()
sess.run(init)
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
if step % 100 == 0:
print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value, duration))
summary_str = sess.run(merged_summaries,feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_file = os.path.join(FLAGS.log_dir, 'model.ckpt')
saver.save(sess, checkpoint_file, global_step=step)
print('Training data eval')
do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.train)
print('Validation data eval')
do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.validation)
print('Test data eval')
do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.test)
#创建日志文件夹,启动训练过程
def main(_):
# if tf.gfile.Exists(FLAGS.log_dir):
# tf.gfile.DeleteRecursively(FLAGS.log_dir)
# tf.gfile.MakeDirs(FLAGS.log_dir)
#启动训练过程
run_training()
#用ArgumentParser类把模型的(超)参数全部解析到全局变量FLAGS里面
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument(
'--learning_rate',
type=float,
default=0.01,
help='Initial learning rate.'
)
parser.add_argument(
'--max_steps',
type=int,
default=2000,
help='Number of steps to run trainer.'
)
parser.add_argument(
'--hidden1',
type=int,
default=128,
help='Number of units in hidden layer 1.'
)
parser.add_argument(
'--hidden2',
type=int,
default=32,
help='Number of units in hidden layer 2.'
)
parser.add_argument(
'--batch_size',
type=int,
default=100,
help='Batch size. Must divide evenly into the dataset sizes.'
)
parser.add_argument(
'--input_data_dir',
type=str,
default='MNIST_data/',
help='Directory to put the input data.'
)
parser.add_argument(
'--log_dir',
type=str,
default='logs/Fully_Connected_Feed',
help='Directory to put the log data.'
)
parser.add_argument(
'--fake_data',
default=False,
help='If true, uses fake data for unit testing.',
action='store_true'
)
#把模型的(超)参数全部解析到全局变量FLAGS里面
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
程序运行结果，
Scalar标量图，
image.png
hidden1/weights 图，
image.png