import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import keras.backend.tensorflow_backend as KTFdef add_layer(inputs,in_size,out_size,activation_function=None):#Weights是一个矩阵，[行，列]为[in_size,out_size]Weights=tf.Variable(tf.random_normal([in_size,out_size]))#正态分布#初始值推荐不为0，所以加上0.1，一行，out_size列biases=tf.Variable(tf.zeros([1,out_size])+0.1)#Weights*x+b的初始化的值，也就是未激活的值Wx_plus_b=tf.matmul(inputs,Weights)+biases#激活if activation_function is None:#激活函数为None，也就是线性函数outputs=Wx_plus_belse:outputs=activation_function(Wx_plus_b)return outputsdef compute_accuracy(prediction, xs, ys, sess, v_xs,v_ys):y_pre=sess.run(prediction,feed_dict={xs:v_xs})correct_prediction=tf.equal(tf.arg_max(y_pre,1),tf.arg_max(v_ys,1))accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))result=sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys})return resultdef train_test_mnist():mnist=input_data.read_data_sets('MNIST_data',one_hot=True)# define placeholder for inputs to networks# 不规定有多少个sample，但是每个sample大小为784（28*28）xs=tf.placeholder(tf.float32,[None,784])ys=tf.placeholder(tf.float32,[None,10])#add output layerprediction=add_layer(xs,784,10,activation_function=tf.nn.softmax)#the error between prediction and real datacross_entropy=tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))train_strp=tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)config = tf.ConfigProto()config.gpu_options.allow_growth = True # 不全部占满显存, 按需分配config.gpu_options.per_process_gpu_memory_fraction = 0.6 #限制GPU内存占用率init=tf.global_variables_initializer()sess = tf.Session(config=config)KTF.set_session(sess) # 设置sessionif True:#with tf.Session() as sess:sess.run(init)for i in range(2000):batch_xs,batch_ys=mnist.train.next_batch(100)sess.run(train_strp,feed_dict={xs:batch_xs,ys:batch_ys})if i%20==0:print("accuracy:", compute_accuracy(prediction, xs, ys, sess, mnist.test.images, mnist.test.labels))def train_test_mnist_visual():#define placeholder for inputs to networkxs=tf.placeholder(tf.float32,[None,64])ys=tf.placeholder(tf.float32,[None,10])#add output layer# l1为隐藏层，为了更加看出overfitting，所以输出给了100l1=add_layer(xs,64,100,'l1',activation_function=tf.nn.tanh)prediction=add_layer(l1,100,10,'l2',activation_function=tf.nn.softmax)def main():train_test_mnist()if __name__ == '__main__':main()
