import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist=input_data.read_data_sets("tmp/data", one_hot=True)learning_rate=0.01 training_epochs=25 batch_size=100 display_step=1

# placeholder x,y 用來(lái)存儲(chǔ)輸入，輸入圖像x構(gòu)成一個(gè)2維的浮點(diǎn)張量，[None,784]是簡(jiǎn)單的平鋪圖，'None'代表處理的批次大小，是任意大小 x=tf.placeholder(tf.float32,[None,784]) y=tf.placeholder(tf.float32,[None,10])# variables 為模型定義權(quán)重和偏置 w=tf.Variable(tf.zeros([784,10])) b=tf.Variable(tf.zeros([10]))pred=tf.nn.softmax(tf.matmul(x,w)+b) # w*x+b要加上softmax函數(shù)

# reduce_sum 對(duì)所有類別求和，reduce_mean 對(duì)和取平均 cost=tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred),reduction_indices=1))

# 往graph中添加新的操作，計(jì)算梯度，計(jì)算參數(shù)的更新 optimizer=tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)init=tf.initialize_all_variables()with tf.Session() as sess:sess.run(init)for epoch in range(training_epochs):total_batch=int(mnist.train.num_examples/batch_size)for i in range(total_batch):batch_xs,batch_ys=mnist.train.next_batch(batch_size)sess.run(optimizer,feed_dict={x:batch_xs,y:batch_ys})if( epoch+1)%display_step==0:print "cost=", sess.run(cost,feed_dict={x:batch_xs,y:batch_ys})prediction=tf.equal(tf.argmax(pred,1),tf.argmax(y,1))accuracy=tf.reduce_mean(tf.cast(prediction,tf.float32))print "Accuracy:" ,accuracy.eval({x:mnist.test.image,y:mnist.test.labels})

　　

logistic 函數(shù)：

二分類問(wèn)題

?

softmax 函數(shù)：

將k維向量壓縮成另一個(gè)k維向量，進(jìn)行多分類，logistic 是softmax的一個(gè)例外

?

轉(zhuǎn)載于:https://www.cnblogs.com/fanhaha/p/7617497.html

總結(jié)

以上是生活随笔為你收集整理的tensorflow--logistic regression的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。