Tensorflow实现Softmax Regression识别手写数字
实现方式:运用单层感知器实现,激活函数采用softmax(),将28*28的图片展开成784维的向量,样本标签采用hotpot的形式,loss函数采用交叉熵,训练算法采用梯度下降算法。
Softmax: σ ( \sigma( σ( z ⃗ ) j = \vec z)_j= z)j= e z j ∑ k = 1 K e z k \frac{e^{z_j}}{\sum_{k=1}^K e^{z_k}} ∑k=1Kezkezj
源代码:
# -*- coding: utf-8 -*-
"""
Created on Sat Jul 20 11:23:29 2019
@author: Administrator
"""
# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
mnist=input_data.read_data_sets('MNIST_data/',one_hot=True)
sess=tf.InteractiveSession()#启动交互式会话
x=tf.placeholder(tf.float32,[None,784])
W=tf.Variable(tf.zeros([784,10]))
b=tf.Variable(tf.zeros([10]))
y=tf.nn.softmax(tf.matmul(x,W)+b)
y_=tf.placeholder(tf.float32,[None,10])
cross_entropy=tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y),reduction_indices=[1]))
train_step=tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
tf.global_variables_initializer().run()
for i in range(1000):#训练1000次,每次顺序取100个样本训练
batch_xs,batch_ys=mnist.train.next_batch(100)
train_step.run({x:batch_xs,y_:batch_ys})
correct_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}))