tensorflow学习教程之文本分类详析

前言

这几天caffe2发布了，支持移动端，我理解是类似单片机的物联网吧应该不是手机之类的，试想iphone7跑CNN，画面太美~

作为一个刚入坑的，甚至还没入坑的人，咱们还是老实研究下tensorflow吧，虽然它没有caffe好上手。tensorflow的特点我就不介绍了：

tensorflow（tf）运算流程：

tensorflow的运行流程主要有2步，分别是构造模型和训练。

在构造模型阶段，我们需要构建一个图(Graph)来描述我们的模型，tensoflow的强大之处也在这了，支持tensorboard:

就类似这样的图，有点像流程图，这里还推荐一个google的tensoflow游乐场，很有意思。

然后到了训练阶段，在构造模型阶段是不进行计算的，只有在tensoflow.Session.run()时会开始计算。

文本分类

先给出代码，然后我们在一一做解释

# -*- coding: utf-8 -*-import pandas as pdimport numpy as npimport tensorflow as tffrom collections import Counterfrom sklearn.datasets import fetch_20newsgroupsdef get_word_2_index(vocab): word2index = {} for i,word in enumerate(vocab): word2index[word] = i return word2indexdef get_batch(df,i,batch_size): batches = [] results = [] texts = df.data[i*batch_size : i*batch_size+batch_size] categories = df.target[i*batch_size : i*batch_size+batch_size] for text in texts: layer = np.zeros(total_words,dtype=float) for word in text.split(' '):  layer[word2index[word.lower()]] += 1 batches.append(layer)  for category in categories: y = np.zeros((3),dtype=float) if category == 0:  y[0] = 1. elif category == 1:  y[1] = 1. else:  y[2] = 1. results.append(y) return np.array(batches),np.array(results)def multilayer_perceptron(input_tensor, weights, biases): #hidden层RELU函数激励 layer_1_multiplication = tf.matmul(input_tensor, weights['h1']) layer_1_addition = tf.add(layer_1_multiplication, biases['b1']) layer_1 = tf.nn.relu(layer_1_addition)  layer_2_multiplication = tf.matmul(layer_1, weights['h2']) layer_2_addition = tf.add(layer_2_multiplication, biases['b2']) layer_2 = tf.nn.relu(layer_2_addition)  # Output layer  out_layer_multiplication = tf.matmul(layer_2, weights['out']) out_layer_addition = out_layer_multiplication + biases['out'] return out_layer_addition#main#从sklearn.datas获取数据cate = ["comp.graphics","sci.space","rec.sport.baseball"]newsgroups_train = fetch_20newsgroups(subset='train', categories=cate)newsgroups_test = fetch_20newsgroups(subset='test', categories=cate)# 计算训练和测试数据总数vocab = Counter()for text in newsgroups_train.data: for word in text.split(' '): vocab[word.lower()]+=1 for text in newsgroups_test.data: for word in text.split(' '): vocab[word.lower()]+=1total_words = len(vocab)word2index = get_word_2_index(vocab)n_hidden_1 = 100 # 一层hidden层神经元个数n_hidden_2 = 100 # 二层hidden层神经元个数n_input = total_words n_classes = 3  # graphics, sci.space and baseball 3层输出层即将文本分为三类#占位input_tensor = tf.placeholder(tf.float32,[None, n_input],name="input")output_tensor = tf.placeholder(tf.float32,[None, n_classes],name="output") #正态分布存储权值和偏差值weights = { 'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])), 'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])), 'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))}biases = { 'b1': tf.Variable(tf.random_normal([n_hidden_1])), 'b2': tf.Variable(tf.random_normal([n_hidden_2])), 'out': tf.Variable(tf.random_normal([n_classes]))}#初始化prediction = multilayer_perceptron(input_tensor, weights, biases)# 定义 loss and optimizer 采用softmax函数# reduce_mean计算平均误差loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=output_tensor))optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss)#初始化所有变量init = tf.global_variables_initializer()#部署 graphwith tf.Session() as sess: sess.run(init) training_epochs = 100 display_step = 5 batch_size = 1000 # Training for epoch in range(training_epochs): avg_cost = 0. total_batch = int(len(newsgroups_train.data) / batch_size) for i in range(total_batch):  batch_x,batch_y = get_batch(newsgroups_train,i,batch_size)  c,_ = sess.run([loss,optimizer], feed_dict={input_tensor: batch_x,output_tensor:batch_y})  # 计算平均损失  avg_cost += c / total_batch # 每5次epoch展示一次loss if epoch % display_step == 0:  print("Epoch:", '%d' % (epoch+1), "loss=", "{:.6f}".format(avg_cost)) print("Finished!") # Test model correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(output_tensor, 1)) # 计算准确率 accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) total_test_data = len(newsgroups_test.target) batch_x_test,batch_y_test = get_batch(newsgroups_test,0,total_test_data) print("Accuracy:", accuracy.eval({input_tensor: batch_x_test, output_tensor: batch_y_test}))