使用TensorFlow完成邏輯回歸

TensorFlow是一種開源的機(jī)器學(xué)習(xí)框架，由Google Brain團(tuán)隊(duì)于2015年開發(fā)。它被廣泛應(yīng)用于圖像和語音識別、自然語言處理、推薦系統(tǒng)等領(lǐng)域。

TensorFlow的核心是用于計(jì)算的數(shù)據(jù)流圖。在數(shù)據(jù)流圖中，節(jié)點(diǎn)表示數(shù)學(xué)操作，邊表示張量（多維數(shù)組）。將操作和數(shù)據(jù)組合在一起的數(shù)據(jù)流圖可以使 TensorFlow 對復(fù)雜的數(shù)學(xué)模型進(jìn)行優(yōu)化，同時(shí)支持分布式計(jì)算。

TensorFlow提供了Python，C++，Java，Go等多種編程語言的接口，讓開發(fā)者可以更便捷地使用TensorFlow構(gòu)建和訓(xùn)練深度學(xué)習(xí)模型。此外，TensorFlow還具有豐富的工具和庫，包括TensorBoard可視化工具、TensorFlow Serving用于生產(chǎn)環(huán)境的模型服務(wù)、Keras高層封裝API等。

TensorFlow已經(jīng)發(fā)展出了許多優(yōu)秀的模型，如卷積神經(jīng)網(wǎng)絡(luò)、循環(huán)神經(jīng)網(wǎng)絡(luò)、生成對抗網(wǎng)絡(luò)等。這些模型已經(jīng)在許多領(lǐng)域取得了優(yōu)秀的成果，如圖像識別、語音識別、自然語言處理等。

除了開源的TensorFlow，Google還推出了基于TensorFlow的云端機(jī)器學(xué)習(xí)平臺Google Cloud ML，為用戶提供了更便捷的訓(xùn)練和部署機(jī)器學(xué)習(xí)模型的服務(wù)。

解決分類問題里最普遍的baseline model就是邏輯回歸，簡單同時(shí)可解釋性好，使得它大受歡迎，我們來用tensorflow完成這個(gè)模型的搭建。

1. 環(huán)境設(shè)定

import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

import warnings
warnings.filterwarnings("ignore")

import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import time

2. 數(shù)據(jù)讀取

#使用tensorflow自帶的工具加載MNIST手寫數(shù)字集合
mnist = input_data.read_data_sets('./data/mnist', one_hot=True) 

Extracting ./data/mnist/train-images-idx3-ubyte.gz
Extracting ./data/mnist/train-labels-idx1-ubyte.gz
Extracting ./data/mnist/t10k-images-idx3-ubyte.gz
Extracting ./data/mnist/t10k-labels-idx1-ubyte.gz

#查看一下數(shù)據(jù)維度
mnist.train.images.shape

(55000, 784)

#查看target維度
mnist.train.labels.shape

(55000, 10)

3. 準(zhǔn)備好placeholder

batch_size = 128
X = tf.placeholder(tf.float32, [batch_size, 784], name='X_placeholder') 
Y = tf.placeholder(tf.int32, [batch_size, 10], name='Y_placeholder')

4. 準(zhǔn)備好參數(shù)/權(quán)重

w = tf.Variable(tf.random_normal(shape=[784, 10], stddev=0.01), name='weights')
b = tf.Variable(tf.zeros([1, 10]), name="bias")

logits = tf.matmul(X, w) + b 

5. 計(jì)算多分類softmax的loss function

# 求交叉熵?fù)p失
entropy = tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=Y, name='loss')
# 求平均
loss = tf.reduce_mean(entropy)

6. 準(zhǔn)備好optimizer

這里的最優(yōu)化用的是隨機(jī)梯度下降，我們可以選擇AdamOptimizer這樣的優(yōu)化器文章來源地址http://www.zghlxwxcb.cn/news/detail-695275.html

learning_rate = 0.01
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(loss)

7. 在session里執(zhí)行g(shù)raph里定義的運(yùn)算

#迭代總輪次
n_epochs = 30

with tf.Session() as sess:
    # 在Tensorboard里可以看到圖的結(jié)構(gòu)
    writer = tf.summary.FileWriter('../graphs/logistic_reg', sess.graph)

    start_time = time.time()
    sess.run(tf.global_variables_initializer())	
    n_batches = int(mnist.train.num_examples/batch_size)
    for i in range(n_epochs): # 迭代這么多輪
        total_loss = 0
        for _ in range(n_batches):
            X_batch, Y_batch = mnist.train.next_batch(batch_size)
            _, loss_batch = sess.run([optimizer, loss], feed_dict={X: X_batch, Y:Y_batch}) 
            total_loss += loss_batch
        print('Average loss epoch {0}: {1}'.format(i, total_loss/n_batches))
    print('Total time: {0} seconds'.format(time.time() - start_time))
    print('Optimization Finished!')

# 測試模型
    preds = tf.nn.softmax(logits)
    correct_preds = tf.equal(tf.argmax(preds, 1), tf.argmax(Y, 1))
    accuracy = tf.reduce_sum(tf.cast(correct_preds, tf.float32))
    
    n_batches = int(mnist.test.num_examples/batch_size)
    total_correct_preds = 0
    
    for i in range(n_batches):
        X_batch, Y_batch = mnist.test.next_batch(batch_size)
        accuracy_batch = sess.run([accuracy], feed_dict={X: X_batch, Y:Y_batch}) 
        total_correct_preds += accuracy_batch[0]
        
    print('Accuracy {0}'.format(total_correct_preds/mnist.test.num_examples))

    writer.close()

   Average loss epoch 0: 0.36748782022571785    
   Average loss epoch 1: 0.2978815356126198    
   Average loss epoch 2: 0.27840628396797845    
   Average loss epoch 3: 0.2783186247437706    
   Average loss epoch 4: 0.2783641471138923    
   Average loss epoch 5: 0.2750668214473413           
   Average loss epoch 6: 0.2687560408126502    
   Average loss epoch 7: 0.2713795114126239    
   Average loss epoch 8: 0.2657588795522154    
   Average loss epoch 9: 0.26322007090686916    
   Average loss epoch 10: 0.26289192279735646    
   Average loss epoch 11: 0.26248606019989873       
   Average loss epoch 12: 0.2604622903056356    
   Average loss epoch 13: 0.26015280702939403    
   Average loss epoch 14: 0.2581879366319496    
   Average loss epoch 15: 0.2590309207117085    
   Average loss epoch 16: 0.2630510463581219    
   Average loss epoch 17: 0.25501730025578767    
   Average loss epoch 18: 0.2547102673000945    
   Average loss epoch 19: 0.258298404375851    
   Average loss epoch 20: 0.2549241428330784    
   Average loss epoch 21: 0.2546788509283866    
   Average loss epoch 22: 0.259556887067837    
   Average loss epoch 23: 0.25428259843365575    
   Average loss epoch 24: 0.25442713139565676    
   Average loss epoch 25: 0.2553852511383159    
   Average loss epoch 26: 0.2503043229415978    
   Average loss epoch 27: 0.25468004046828596    
   Average loss epoch 28: 0.2552785321479633    
   Average loss epoch 29: 0.2506257003663859    
   Total time: 28.603315353393555 seconds    
   Optimization Finished!    
   Accuracy 0.9187

附：系列文章

到了這里，關(guān)于【深度學(xué)習(xí)】實(shí)驗(yàn)07 使用TensorFlow完成邏輯回歸的文章就介紹完了。如果您還想了解更多內(nèi)容，請?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！