手把手教你用 TensorFlow 實現文本分類（下）

本文作者： AI研習社

2017-05-29 13:36

導語：文本分類全流程解析。

雷鋒網按：本文作者張慶恒，原文載于作者個人博客，雷鋒網(公眾號：雷鋒網)已獲授權。

本篇文章主要記錄對之前用神經網絡做文本識別的初步優(yōu)化，進一步將準確率由原來的65%提高到80%，這里優(yōu)化的幾個方面包括：

● 隨機打亂訓練數據
● 增加隱層，和驗證集
● 正則化
● 對原數據進行PCA預處理
● 調節(jié)訓練參數（迭代次數，batch大小等）

隨機化訓練數據

觀察訓練數據集，發(fā)現訓練集是按類別存儲，讀進內存后在仍然是按類別順序存放。這樣順序取一部分作為驗證集，很大程度上會減少一個類別的訓練樣本數，對該類別的預測準確率會有所下降。所以首先考慮打亂訓練數據。

在已經向量化的訓練數據的基礎上打亂數據，首先合并data和label，打亂后再將數據和標簽分離為trian.txt和train_label.txt。這里可以直接使用shell命令：

1、將labels加到trian.txt的第一列

paste -d" " train_labels.txt train.txt > train_to_shuf.txt

2、隨機打亂文件行

shuf train_to_shuf.txt -o train.txt

3、提取打亂后文件的第一列，保存到train_labels.txt

cat train.txt | awk '{print $1}' > train_labels.txt

4、刪除第一列l(wèi)abel.

awk '{$1="";print $0}' train.txt

這樣再次以相同方式訓練，準確率由65%上升到75% 。

改變網絡結構，增加隱層

之前的網絡直接對輸入數據做softmax回歸，這里考慮增加隱層，數量并加入驗證集觀察準確率的變化情況。這里加入一個隱層，隱層節(jié)點數為500，激勵函數使用Relu。替換原來的網絡結構，準確率進一步上升。

正則化，改善過擬合

觀察模型對訓練集的擬合程度到90%+，而通過上步對訓練數據的準確率為76%，一定程度上出現了過擬合的現象，這里在原有cost function中上加入正則項，希望減輕過擬合的現象。這里使用L2正則。連同上步部分的代碼如下：

#!/usr/bin/python
#-*-coding:utf-8-*-

LAYER_NODE1 = 500 # layer1 node num
INPUT_NODE = 5000
OUTPUT_NODE = 10
REG_RATE = 0.01

import tensorflow as tf
from datasets import datasets

def interface(inputs, w1, b1, w2,b2):
"""
compute forword progration result
"""
lay1 = tf.nn.relu(tf.matmul(inputs, w1) + b1)
return tf.nn.softmax(tf.matmul(lay1, w2) + b2) # need softmax??

data_sets = datasets()
data_sets.read_train_data(".", True)

sess = tf.InteractiveSession()

x = tf.placeholder(tf.float32, [None, INPUT_NODE], name="x-input")
y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name="y-input")

w1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER_NODE1], stddev=0.1))
b1 = tf.Variable(tf.constant(0.0, shape=[LAYER_NODE1]))

w2 = tf.Variable(tf.truncated_normal([LAYER_NODE1, OUTPUT_NODE], stddev=0.1))
b2 = tf.Variable(tf.constant(0.0, shape=[OUTPUT_NODE]))

y = interface(x, w1, b1, w2, b2)

cross_entropy = -tf.reduce_sum(y_ * tf.log(y + 1e-10))
regularizer = tf.contrib.layers.l2_regularizer(REG_RATE)
regularization = regularizer(w1) + regularizer(w2)
loss = cross_entropy + regularization

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(loss)

#training
tf.global_variables_initializer().run()
saver = tf.train.Saver()

cv_feed = {x: data_sets.cv.text, y_: data_sets.cv.label}
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
acc = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

for i in range(5000):
if i % 200 == 0:
cv_acc = sess.run(acc, feed_dict=cv_feed)
print "train steps: %d, cv accuracy is %g " % (i, cv_acc)
batch_xs, batch_ys = data_sets.train.next_batch(100)
train_step.run({x: batch_xs, y_: batch_ys})

path = saver.save(sess, "./model4/model.md")

PCA處理

一方面對文本向量集是嚴重稀疏的矩陣，而且維度較大，一方面影響訓練速度，一方面消耗內存。這里考慮對數據進行PCA處理。該部分希望保存99%的差異率，得到相應的k，即對應的維度。

#!/usr/bin/python
#-*-coding:utf-8-*-
"""
PCA for datasets

"""
import os
import sys
import commands
import numpy
from contextlib import nested
from datasets import datasets

ORIGIN_DIM = 5000

def pca(origin_mat):
"""
gen matrix using pca
row of origin_mat is one sample of dataset
col of origin_mat is one feature
return matrix U, s and V
"""
# mean,normaliza1on
avg = numpy.mean(origin_mat, axis=0)
# covariance matrix
cov = numpy.cov(origin_mat-avg,rowvar=0)
#Singular Value Decomposition
U, s, V = numpy.linalg.svd(cov, full_matrices=True)

k = 1;
sigma_s = numpy.sum(s)
# chose smallest k for 99% of variance retained
for k in range(1, ORIGIN_DIM+1):
variance = numpy.sum(s[0:k]) / sigma_s
print "k = %d, variance is %f" % (k, variance)
if variance >= 0.99:
break

if k == ORIGIN_DIM:
print "some thing unexpected , k is same as ORIGIN_DIM"
exit(1)

return U[:, 0:k], k

if __name__ == '__main__':
"""
main, read train.txt, and do pca
save file to train_pca.txt
"""
data_sets = datasets()
train_text, _ = data_sets.read_from_disk(".", "train", one_hot=False)

U, k = pca(train_text)
print "U shpae: ", U.shape
print "k is : ", k

text_pca = numpy.dot(train_text, U)
text_num = text_pca.shape[0]
print "text_num in pca is ", text_num

with open("./train_pca.txt", "a+") as f:
for i in range(0, text_num):
f.write(" ".join(map(str, text_pca[i,:])) + "\n")