tensorflow+python flask进行手写识别_Tensorflow训练识别手写数字0-9

1.安装环境

这个比较简单，

1.1 安装cnetos7 这个版本中直接代有python2.7.5版本，(下载ISO安装包安装即可我用的是vmware12.5)

1.2 安装 tensorflow

安装pip

yum update -y && yum install -y python python-devel epel-release.noarch python-pip

使用pip安装tensorflow

pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.5.0-cp27-none-linux_x86_64.whl

1.3 安装 python flaskapi

pip install flask(这个不记得了，不行就度娘吧)

1.5 下载MNIST训练库

mnist库

https://files.cnblogs.com/files/keim/train-images-idx3-ubyte.gz.rar 这个文件后缀Rar去掉

https://files.cnblogs.com/files/keim/MNIST_data1.rar   解压和上面的放一起即可

2.训练代码

如下是训练代码，其中mnist_data为上面的MNIST库的位置

#coding=utf-8

from tensorflow.examples.tutorials.mnist importinput_data

mnist= input_data.read_data_sets('MNIST_data', one_hot=True)importtensorflow as tf

sess=tf.InteractiveSession()

x= tf.placeholder(tf.float32, shape=[None, 784])

y_= tf.placeholder(tf.float32, shape=[None, 10])

W= tf.Variable(tf.zeros([784,10]))

b= tf.Variable(tf.zeros([10]))

sess.run(tf.global_variables_initializer())

y= tf.matmul(x,W) +b

cross_entropy=tf.reduce_mean(

tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))

train_step= tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)for _ in range(1000):

batch= mnist.train.next_batch(100)

train_step.run(feed_dict={x: batch[0], y_: batch[1]})

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(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))defweight_variable(shape):

initial= tf.truncated_normal(shape, stddev=0.1)returntf.Variable(initial)defbias_variable(shape):

initial= tf.constant(0.1, shape=shape)returntf.Variable(initial)defconv2d(x, W):return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')defmax_pool_2x2(x):return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],

strides=[1, 2, 2, 1], padding='SAME')

W_conv1= weight_variable([5, 5, 1, 32])

b_conv1= bias_variable([32])

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)

W_conv2= weight_variable([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)

W_fc1= weight_variable([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)

keep_prob=tf.placeholder(tf.float32)

h_fc1_drop=tf.nn.dropout(h_fc1, keep_prob)

W_fc2= weight_variable([1024, 10])

b_fc2= bias_variable([10])

y_conv= tf.matmul(h_fc1_drop, W_fc2) +b_fc2

cross_entropy=tf.reduce_mean(

tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))

train_step= tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction= tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))

accuracy=tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

saver= tf.train.Save