参考:
《TensorFlow技术解析与实战》
http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/mnist_beginners.html
http://www.jianshu.com/p/4195577585e6
http://blog.csdn.net/u014422406/article/details/52805924
#########################################################################################################
MNIST分类问题-Softmax回归
# -*- coding:utf-8 -*-
# ==============================================================================
# 20171114
# HelloZEX
# ==============================================================================
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
#使用input_data.py文件来加载数据
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
FLAGS = None
def main(_):
# 导入数据
mnist = input_data.read_data_sets("MNIST_Labels_Images", one_hot=True)
# 构建回归模型
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 #预测值
# 定义损失函数和优化器
y_ = tf.placeholder(tf.float32, [None, 10])
# 交叉熵的原始公式,
# tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),reduction_indices=[1]))
# 数值上不稳定
# 这里我们使用的是 tf.nn.softmax_cross_entropy_with_logits
# 输出y后求均值
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
#采用SGD(随机梯度下降法)作为优化器
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
#训练模型
#创建交互式的TF会话
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
# 训练数据
for _ in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
# 评估模型
#tf.argmax(y_, 1)返回的是模型对任意一输入x的预测到的标记值
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print("正确率:", sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
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)
console:
/usr/bin/python2.7 /home/zhengxinxin/Desktop/PyCharm/pycharm-community-2017.2/helpers/pydev/pydevd.py --multiproc --qt-support=auto --client 127.0.0.1 --port 34763 --file /home/zhengxinxin/Desktop/PyCharm/Spark/SparkMNIST/mnist_softmax.py
pydev debugger: process 3248 is connecting
Connected to pydev debugger (build 172.3544.44)
Extracting MNIST_Labels_Images/train-images-idx3-ubyte.gz
Extracting MNIST_Labels_Images/train-labels-idx1-ubyte.gz
Extracting MNIST_Labels_Images/t10k-images-idx3-ubyte.gz
Extracting MNIST_Labels_Images/t10k-labels-idx1-ubyte.gz
2017-11-14 19:53:24.149759: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-11-14 19:53:24.149807: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-11-14 19:53:24.149812: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-11-14 19:53:24.149815: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-11-14 19:53:24.149819: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
正确率: 0.9172
Process finished with exit code 0
#########################################################################################################