#mnist.py
# 1.导入模块
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import tensorflow as tf
# 2.系统参数，让程序更直观，方便修改
# 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
# 3.神经网络图
# 输入：输入图片，隐藏层1神经元个数，隐藏层2神经元个数
# 输出：神经网络输出
def inference(images, hidden1_units, hidden2_units):
# 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
# 4.输出损失计算方法
# 输入参数 logits：网络输出，为float类型，[batch_size,NUM_CLASSES]
# labels：目标标签，为int32类型，[batch_size]
# 输出：损失，float类型
def loss(logits, labels):
labels = tf.to_int64(labels)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=labels, logits=logits, name='xentropy')
return tf.reduce_mean(cross_entropy, name='xentropy_mean')
# 5.训练方法
# 输入：损失，学习速率
# 输出：训练op
# 训练方法为梯度下降。
def training(loss, learning_rate):
# Add a scalar summary for the snapshot loss.
tf.summary.scalar('loss', 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
# 6.评估训练效果
# 输入：logits：网络输出，float32，[batch_size, NUM_CLASSES]
# labels：标签，int32，[batch_size]
# 输出：预测正确的数量
def evaluation(logits, labels):
correct = tf.nn.in_top_k(logits, labels, 1)
return tf.reduce_sum(tf.cast(correct, tf.int32))#fully_connected_feed.py
"""Trains and Evaluates the MNIST network using a feed dictionary."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
# pylint: disable=missing-docstring
import argparse
import os
import sys
import time
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.
FLAGS = None
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
def do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_set):
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 = float(true_count) / num_examples
print('Num examples: %d Num correct: %d Precision @ 1: %0.04f' %
(num_examples, true_count, precision))
def run_training():
data_sets = input_data.read_data_sets(FLAGS.input_data_dir, FLAGS.fake_data)
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 Tensor based on the TF collection of Summaries.
summary = tf.summary.merge_all()
# Add the variable initializer Op.
init = tf.global_variables_initializer()
# Create a saver for writing training checkpoints.
saver = tf.train.Saver()
# Create a session for running Ops on the Graph.
sess = tf.Session()
# Instantiate a SummaryWriter to output summaries and the Graph.
summary_writer = tf.summary.FileWriter(FLAGS.log_dir, sess.graph)
# Run the Op to initialize the variables.
sess.run(init)
# 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, feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
# Save a checkpoint and evaluate the model periodically.
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)
# 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(_):
if tf.gfile.Exists(FLAGS.log_dir):
tf.gfile.DeleteRecursively(FLAGS.log_dir)
tf.gfile.MakeDirs(FLAGS.log_dir)
run_training()
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=os.path.join(os.getenv('TEST_TMPDIR', './tmp'),
'tensorflow/mnist/input_data'),
help='Directory to put the input data.'
)
parser.add_argument(
'--log_dir',
type=str,
default=os.path.join(os.getenv('TEST_TMPDIR', './tmp'),
'tensorflow/mnist/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'
)
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
训练结果及目录结构：
启动tensorboard数据可视化：
1.找到训练输出文件，复制该地址2.打开cmd,进入该文件夹，
3输入tensorboard.exe --logdir=“文件所在目录”
4.打开浏览器输入localhost:6006