TensorFlow实现简单的手写字体识别

最新推荐文章于 2024-08-13 22:48:20 发布

IT-行者

最新推荐文章于 2024-08-13 22:48:20 发布

阅读量3.8k

点赞数 2

分类专栏： TensorFlow

本文链接：https://blog.csdn.net/Explorer_Du/article/details/60140183

版权

#读取mnist数据集

import tensorflow as tf
from  tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/",one_hot = True)


#设置参数的大小
sess = tf.InteractiveSession()
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])

#loss function为cross_entropy
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)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
#训练
for i in range(1000):
	batch_xs,batch_ys