本文實例為大家分享了TensorFlow實現(xiàn)Logistic回歸的具體代碼，供大家參考，具體內(nèi)容如下

1.導入模塊

import numpy as npimport pandas as pdfrom pandas import Series,DataFramefrom matplotlib import pyplot as plt%matplotlib inline#導入tensorflowimport tensorflow as tf#導入MNIST(手寫數(shù)字數(shù)據(jù)集)from tensorflow.examples.tutorials.mnist import input_data

2.獲取訓練數(shù)據(jù)和測試數(shù)據(jù)

import ssl ssl._create_default_https_context = ssl._create_unverified_contextmnist = input_data.read_data_sets('./TensorFlow',one_hot=True)test = mnist.testtest_images = test.imagestrain = mnist.trainimages = train.images

3.模擬線性方程

#創(chuàng)建占矩陣位符X,YX = tf.placeholder(tf.float32,shape=[None,784])Y = tf.placeholder(tf.float32,shape=[None,10])#隨機生成斜率W和截距bW = tf.Variable(tf.zeros([784,10]))b = tf.Variable(tf.zeros([10]))#根據(jù)模擬線性方程得出預測值y_pre = tf.matmul(X,W)+b#將預測值結(jié)果概率化y_pre_r = tf.nn.softmax(y_pre)

4.構(gòu)造損失函數(shù)

# -y*tf.log(y_pre_r) --->-Pi*log(Pi)  信息熵公式cost = tf.reduce_mean(-tf.reduce_sum(Y*tf.log(y_pre_r),axis=1))

5.實現(xiàn)梯度下降，獲取最小損失函數(shù)

#learning_rate:學習率,是進行訓練時在最陡的梯度方向上所采取的「步」長；learning_rate = 0.01optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

6.TensorFlow初始化，并進行訓練

#定義相關(guān)參數(shù)#訓練循環(huán)次數(shù)training_epochs = 25#batch 一批，每次訓練給算法10個數(shù)據(jù)batch_size = 10#每隔5次，打印輸出運算的結(jié)果display_step = 5#預定義初始化init = tf.global_variables_initializer()#開始訓練with tf.Session() as sess:  #初始化  sess.run(init)  #循環(huán)訓練次數(shù)  for epoch in range(training_epochs):    avg_cost = 0.    #總訓練批次total_batch =訓練總樣本量/每批次樣本數(shù)量    total_batch = int(train.num_examples/batch_size)    for i in range(total_batch):      #每次取出100個數(shù)據(jù)作為訓練數(shù)據(jù)      batch_xs,batch_ys = mnist.train.next_batch(batch_size)      _, c = sess.run([optimizer,cost],feed_dict={X:batch_xs,Y:batch_ys})      avg_cost +=c/total_batch    if(epoch+1)%display_step == 0:      print(batch_xs.shape,batch_ys.shape)      print('epoch:','%04d'%(epoch+1),'cost=','{:.9f}'.format(avg_cost))  print('Optimization Finished!')  #7.評估效果  # Test model  correct_prediction = tf.equal(tf.argmax(y_pre_r,1),tf.argmax(Y,1))  # Calculate accuracy for 3000 examples  # tf.cast類型轉(zhuǎn)換  accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))  print("Accuracy:",accuracy.eval({X: mnist.test.images[:3000], Y: mnist.test.labels[:3000]}))

以上就是本文的全部內(nèi)容，希望對大家的學習有所幫助，也希望大家多多支持武林站長站。