逻辑回归模型

逻辑回归是应用非常广泛的一个分类机器学习算法，它将数据拟合到一个logit函数(或者叫做logistic函数)中，从而能够完成对事件发生的概率进行预测。

import numpy as npimport tensorflow as tfimport matplotlib.pyplot as pltfrom tensorflow.examples.tutorials.mnist import input_data#下载好的mnist数据集存在F:/mnist/data/中mnist = input_data.read_data_sets('F:/mnist/data/',one_hot = True)print(mnist.train.num_examples)print(mnist.test.num_examples)trainimg = mnist.train.imagestrainlabel = mnist.train.labelstestimg = mnist.test.imagestestlabel = mnist.test.labelsprint(type(trainimg))print(trainimg.shape,)print(trainlabel.shape,)print(testimg.shape,)print(testlabel.shape,)nsample = 5randidx = np.random.randint(trainimg.shape[0],size = nsample)for i in randidx: curr_img = np.reshape(trainimg[i,:],(28,28)) curr_label = np.argmax(trainlabel[i,:]) plt.matshow(curr_img,cmap=plt.get_cmap('gray')) plt.title(""+str(i)+"th Training Data"+"label is"+str(curr_label)) print(""+str(i)+"th Training Data"+"label is"+str(curr_label)) plt.show()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]))#actv = tf.nn.softmax(tf.matmul(x,W)+b)#计算损失cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(actv),reduction_indices=1))#学习率learning_rate = 0.01#随机梯度下降optm = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)#求1位置索引值 对比预测值索引与label索引是否一样，一样返回Truepred = tf.equal(tf.argmax(actv,1),tf.argmax(y,1))#tf.cast把True和false转换为float类型 0，1#把所有预测结果加在一起求精度accr = tf.reduce_mean(tf.cast(pred,"float"))init = tf.global_variables_initializer()"""#测试代码 sess = tf.InteractiveSession()arr = np.array([[31,23,4,24,27,34],[18,3,25,4,5,6],[4,3,2,1,5,67]])#返回数组的维数 2print(tf.rank(arr).eval())#返回数组的行列数 [3 6]print(tf.shape(arr).eval())#返回数组中每一列中最大元素的索引[0 0 1 0 0 2]print(tf.argmax(arr,0).eval())#返回数组中每一行中最大元素的索引[5 2 5]print(tf.argmax(arr,1).eval()) J"""#把所有样本迭代50次training_epochs = 50#每次迭代选择多少样本batch_size = 100display_step = 5sess = tf.Session()sess.run(init)#循环迭代for epoch in range(training_epochs): avg_cost = 0 num_batch = int(mnist.train.num_examples/batch_size) for i in range(num_batch): batch_xs,batch_ys = mnist.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 if epoch % display_step ==0: feeds_train = {x:batch_xs,y:batch_ys} feeds_test = {x:mnist.test.images,y:mnist.test.labels} train_acc = sess.run(accr,feed_dict = feeds_train) test_acc = sess.run(accr,feed_dict = feeds_test) #每五个epoch打印一次信息 print("Epoch:%03d/%03d cost:%.9f train_acc:%.3f test_acc: %.3f" %(epoch,training_epochs,avg_cost,train_acc,test_acc))print("Done")

程序训练结果如下：

Epoch:000/050 cost:1.177228655 train_acc:0.800 test_acc: 0.855Epoch:005/050 cost:0.440933891 train_acc:0.890 test_acc: 0.894Epoch:010/050 cost:0.383387268 train_acc:0.930 test_acc: 0.905Epoch:015/050 cost:0.357281335 train_acc:0.930 test_acc: 0.909Epoch:020/050 cost:0.341473956 train_acc:0.890 test_acc: 0.913Epoch:025/050 cost:0.330586549 train_acc:0.920 test_acc: 0.915Epoch:030/050 cost:0.322370980 train_acc:0.870 test_acc: 0.916Epoch:035/050 cost:0.315942993 train_acc:0.940 test_acc: 0.916Epoch:040/050 cost:0.310728854 train_acc:0.890 test_acc: 0.917Epoch:045/050 cost:0.306357428 train_acc:0.870 test_acc: 0.918Done

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。