导入minst数据集
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import input_data
minst=input_data.read_data_sets('data/',one_hot=True)
定义
trainimg=minst.train.images
trainlabel=minst.train.labels
testimg=minst.test.images
testlabel=minst.test.labels
逻辑回归模型框架
#x,y先不赋值 784个像素点,10个分类,None是无穷
x=tf.placeholder('float',[None,784])
y=tf.placeholder('float',[None,10])
W=tf.Variable(tf.zeros([784,10]))
b=tf.Variable(tf.zeros([10]))
#softmax传进去属于0-10哪一个数字的分值大
actv=tf.nn.softmax(tf.matmul(x,W)+b)
#cost function :-log(P),P:属于真实值的概率
cost=tf.reduce_mean(-tf.reduce_sum(y*tf.log(actv),reduction_indices=1))
#optimizer
learning_rate=0.01
optm=tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
测试
#prediction
pred=tf.equal(tf.argmax(actv,1),tf.argmax(y,1))
#accuracy
accr=tf.reduce_mean(tf.cast(pred,"float"))
#initializer
init=tf.global_variables_initializer()
迭代
#样本迭代50次,每次选择100个样本
training_epochs=50
batch_size=100
display_step=5
#session
sess=tf.Session()
sess.run(init)
#mini-batch leaning
for epoch in range(training_epochs):
avg_cost=0
num_batch=int(minst.train.num_examples/batch_size)
for i in range(num_batch):
batch_xs,batch_ys=minst.train.next_batch(batch_size)
sess.run(optm,feed_dict={x:batch_xs,y:batch_ys})
feeds={x:batch_xs,y:batch_ys}
avg_cost+=sess.run(cost,feed_dict=feeds)/num_batch
#display
if epoch % display_step==0:
feeds_train={x:batch_xs,y:batch_ys}
feeds_test={x:minst.test.images,y:minst.test.labels}
train_acc=sess.run(accr,feed_dict=feeds_train)
test_acc=sess.run(accr,feed_dict=feeds_test)
print("Epoch:%03d%03d cost: %9f train_acc: %3f test_acc: %3f"%(epoch,training_epochs,avg_cost,train_acc,test_acc))
print("Done")
从结果看训练效果还不错: