手写数字识别tf1.0

import tensorflow as tf
mnist
mnist.train
mnist.validation
mnist.test
#图像显示函数
import matplotlib.pyplot as plt
def plot_image(image):
    plt.inshow(image.reshape(28,28),cmap="binary")
#输入数据
x=tf.placeholder(tf.float32，[None,784])
y=tf.placeholder(tf.float32,[None,10])
#定义变量
w=tf.Variable(tf.random_normal([784,10]))
b=tf.Variable(tf.zero([10]))
#模型构建
forward=tf.matmul(x,W)+b
pred=tf.nn.softmax(forward)
#损失函数
loss_function=#交叉熵函数
#优化函数
optimizer=tf.train.GradientDenscentOptimizer(learning_rate).minimize(loss_function)
#准确率
correct_prefiction=tf.equal(tf.argmax(pred,1),tf.argmax(y,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32)
#创建对话
sess=tf.Sessin()
init=tf.global_variables_initializer()
sess.run(init)
#训练模型
for epoch in range(train_epochs):
    for batch in range(total_batch):
        xs,ys=mnist.train.next_batc(batch_size)
        sess.run(optimizer,feed_dict={x:xs,y:ys})
    loss,acc = sess.run([loss_function,accuracy],feed_dict={x:mnist.validation.image,y:mnist.validation.;ables})
    if(epoch)%display_step==0:
        pass#打印准确率和损失值

#在测试集上评估模型准确率
accu_test = sess.run(accurary,feed_dict={x:mnist.test.images,y:mnist.test.lables})
#应用模型
prediction_result=sess.run(tf.argmax(pred,1),feed_dict={x:mnist.test.images})

---

多层神经网络

#两层隐藏层
H1_NN=256
H2_NN=64

w1=tf.Variable(tf.truncated_normal([784,H1_NN],stddev=0.1)
b1=tf.Variable(tf.zero([H1_NN))

w2=tf.Variable(tf.truncated_normal([H1_NN,H2_NN],stddev=0.1))
b2=tf.Variable(tf.zero([H2_NN]))

w3=tf.Variable(tf.truncated_normal([H2_NN,10],stddev=0.1))
b3=tf.Variable(tf.zero([10]))

Y1=tf.nn.relu(tf.matul(x,w1)+b1)
Y2=tf.nn.relu(tf.matul(x,w2)+b2)
forward=tf.matul(Y1,w3)+b3
pred=tf.nn.softmax(forward)

---