TensorFlow 实现Softmax Regression识别手写数字

使用TensorFlow实现一个简单的机器学习算法Softmax Regression，一个没有隐含层的最浅的神经网络。环境：Ubuntu + Anaconda（Spyder） + TensorFlow数据：MNIST（Mixed National Institute of Standards and Technology database）步骤：1）定义算法公司，也就是神经网络forward时的计算。2）定义loss，选定优化器，并指定优化器优化loss。3）迭代地对数据进行训练。4）在测试集或验证集上对准确率进行评测。

---

太多的理论赛不过代码的理解，下面见整个代码和注释。

#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Thu Sep 14 16:33:11 2017Softmax Regression using TensorFlow@author: z"""##import dataimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data  mnist =input_data.read_data_sets("MNIST_data/", one_hot=True) #Print the shape of mistprint('\n','mnist.train.images.shape,mnist.train.labels.shape')print(mnist.train.images.shape,mnist.train.labels.shape)#(55000, 784) (55000, 10)     ##28*28=784print('mnist.test.images.shape, mnist.train.labels.shape')print(mnist.test.images.shape, mnist.train.labels.shape)#(10000, 784) (55000, 10)print('mnist.validation.images.shape, mnist.validation.labels.shape')print(mnist.validation.images.shape, mnist.validation.labels.shape)#(5000, 784) (5000, 10)## 2.Create the model#create sesssess=tf.InteractiveSession()#put-data , first var is datatype, second is tensor shapex=tf.placeholder(tf.float32,[None,784])#Weights and bias are initialized to zeroW=tf.Variable(tf.zeros([784,10]))  b=tf.Variable(tf.zeros([10]))#realize Softmax Regression: y=sotfmax(Wx+b)y=tf.nn.softmax(tf.matmul(x,W)+b)# Define lossy_ = tf.placeholder(tf.float32, [None, 10])cross_entropy = tf.reduce_mean(    -tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))#Define optimizertrain_step=tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy) tf.global_variables_initializer().run()  ## 3.Trainfor i in range(1000):    batch_xs, batch_ys = mnist.train.next_batch(100)    train_step.run({x: batch_xs, y_: batch_ys})## 4.Test trained modelcorrect_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))print(accuracy.eval({x: mnist.test.images,y_: mnist.test.labels}))