使用CNN实现手写体识别(minist库)
来源:互联网 发布:人工智能 教育风口 编辑:程序博客网 时间:2024/05/20 05:31
入门级CNN代码
有空在下一篇写写CNN原理
# -*- coding: utf-8 -*-"""Created on Wed Oct 11 16:51:27 2017@author: tina"""import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datadef weight_varible(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')mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)print("Download Done!")sess = tf.InteractiveSession()# parasW_conv1 = weight_varible([5, 5, 1, 32])b_conv1 = bias_variable([32])# conv layer-1x = tf.placeholder(tf.float32, [None, 784])x_image = tf.reshape(x, [-1, 28, 28, 1])h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1)# conv layer-2W_conv2 = weight_varible([5, 5, 32, 64])b_conv2 = bias_variable([64])h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)h_pool2 = max_pool_2x2(h_conv2)# full connectionW_fc1 = weight_varible([7 * 7 * 64, 1024])b_fc1 = 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_fc1) + b_fc1)# dropoutkeep_prob = tf.placeholder(tf.float32)h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)# output layer: softmaxW_fc2 = weight_varible([1024, 10])b_fc2 = bias_variable([10])y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)y_ = tf.placeholder(tf.float32, [None, 10])# model trainingcross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)correct_prediction = tf.equal(tf.arg_max(y_conv, 1), tf.arg_max(y_, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))sess.run(tf.initialize_all_variables())for i in range(20000): batch = mnist.train.next_batch(50) if i % 100 == 0: train_accuacy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0}) print("step %d, training accuracy %g"%(i, train_accuacy)) train_step.run(feed_dict = {x: batch[0], y_: batch[1], keep_prob: 0.5})# accuacy on testprint("test accuracy %g"%(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})))
效果
阅读全文
0 0
- 使用CNN实现手写体识别(minist库)
- 利用CNN实现手写体识别
- libsvm Minist Hog 手写体识别
- libsvm Minist Hog 手写体识别
- CNN学习(三)—Tensorflow 进行MNIST手写体识别
- 使用k近邻算法实现手写体识别
- python tensorflow 使用minist数据集实现手写数字识别
- Tensorflow学习:MINIST手写体
- 用CNN解决手写体数字识别。--tensorflow
- 使用K近邻算法实现手写体识别系统
- 用CNN及MLP等方法识别minist数据集
- 使用KNN算法手写体识别
- 对于二次型损失函数在minist手写体识别中是否合理的理解
- Deeplearning4j 实战(2):Deeplearning4j 手写体数字识别Spark实现
- 手写体识别(基于Opencv)
- tensorflow手写体识别(一)
- 深度学习笔记——TensorFlow学习笔记(三)使用TensorFlow实现的神经网络进行MNIST手写体数字识别
- 手写体识别
- Spring学习笔记3
- 关于Python里split()函数的用法
- Linux内核追踪[4.13] Blk层的出错处理优化
- OSGi规范与原理(2)--模块化
- INFP职业规划,24女孩的“环旅插画师”梦想
- 使用CNN实现手写体识别(minist库)
- Centos中的程序开机自启动
- React 属性和状态
- 麻将简单胡牌算法
- 车辆管理系统
- 环境变量,mv命令,cp命令,几个查看文件的命令
- 最实用的Git 教程
- 文章标题
- 第七周项目2—建立链队算法库