前提
- 首先确保安装tensorflow,建议采用virtualenv或者docker方式。
- 以下代码基于python3.5+tensorflow
基本代码
# 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 very simple MNIST classifier.
See extensive documentation at
http://tensorflow.org/tutorials/mnist/beginners/index.md
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
# Import data
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
FLAGS = None
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
def main(_):
mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)
# Create the model
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.matmul(x, W) + b
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
# create the CNN model
# 1.1 cov 1
w1 = weight_variable([6, 6, 1, 32])
b1 = bias_variable([32])
x_image = tf.reshape(x,[-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image, w1) + b1)
# 1.2 max 1
h_pool1 = max_pool_2x2(h_conv1)
# 2.2 cov 2
w2 = weight_variable([6,6,32,64])
b2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, w2) + b2)
# 2.2 max 2
h_pool2 = max_pool_2x2(h_conv2)
# full connecting layer
w_fc = weight_variable([7*7*64, 1024])
b_fc = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc) + b_fc)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# maxsoft layer
w_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
for i in range(2000):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x: batch[0], y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g" % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print("test accuracy %g" % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--data_dir', type=str, default='/tmp/tensorflow/mnist/input_data',
help='Directory for storing input data')
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
输出
- step 0, training accuracy 0.06
- step 100, training accuracy 0.86
- step 200, training accuracy 0.94
- step 300, training accuracy 0.88
- step 400, training accuracy 1
- step 500, training accuracy 0.9
- step 600, training accuracy 0.98
- step 700, training accuracy 0.96
- step 800, training accuracy 0.94
- step 900, training accuracy 1
- step 1000, training accuracy 0.94
- step 1100, training accuracy 0.94
- step 1200, training accuracy 0.96
- step 1300, training accuracy 0.96
- step 1400, training accuracy 0.94
- step 1500, training accuracy 0.96
- step 1600, training accuracy 0.98
- step 1700, training accuracy 0.96
- step 1800, training accuracy 0.96
- step 1900, training accuracy 0.96
- test accuracy 0.9736