RNN与情感分类问题实战-加载IMDB数据集
Sentiment Analysis
Two approaches
SimpleRNNCell
single layer
multi-layers
RNNCell
Single layer
import os
import tensorflow as tf
import numpy as np
from tensorflow import keras
from tensorflow.keras import layers
tf.random.set_seed(22)
np.random.seed(22)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
assert tf.__version__.startswith('2.')
batchsz = 128
# the most frequest words
total_words = 10000
max_review_len = 80
embedding_len = 100
(x_train,
y_train), (x_test,
y_test) = keras.datasets.imdb.load_data(num_words=total_words)
# x_train:[b, 80]
# x_test: [b, 80]
x_train = keras.preprocessing.sequence.pad_sequences(x_train,
maxlen=max_review_len)
x_test = keras.preprocessing.sequence.pad_sequences(x_test,
maxlen=max_review_len)
db_train = tf.data.Dataset.from_tensor_slices((x_train, y_train))
db_train = db_train.shuffle(1000).batch(batchsz, drop_remainder=True)
db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test))
db_test = db_test.batch(batchsz, drop_remainder=True)
print('x_train shape:', x_train.shape, tf.reduce_max(y_train),
tf.reduce_min(y_train))
print('x_test shape:', x_test.shape)
class MyRNN(keras.Model):
def __init__(self, units):
super(MyRNN, self).__init__()
# [b, 64]
self.state0 = [tf.zeros([batchsz, units])]
self.state1 = [tf.zeros([batchsz, units])]
# transform text to embedding representation
# [b, 80] => [b, 80, 100]
self.embedding = layers.Embedding(total_words,
embedding_len,
input_length=max_review_len)
# [b, 80, 100] , h_dim: 64
# RNN: cell1 ,cell2, cell3
# SimpleRNN,units=64表示100个向量转成64个初始的状态
self.rnn_cell0 = layers.SimpleRNNCell(units, dropout=0.5)
self.rnn_cell1 = layers.SimpleRNNCell(units, dropout=0.5)
# fc, [b, 80, 100] => [b, 64] => [b, 1]
self.outlayer = layers.Dense(1)
def call(self, inputs, training=None):
"""
net(x) net(x, training=True) :train mode
net(x, training=False): test
:param inputs: [b, 80]
:param training:
:return:
"""
# [b, 80]
x = inputs
# embedding: [b, 80] => [b, 80, 100]
x = self.embedding(x)
# rnn cell compute
# [b, 80, 100] => [b, 64]
state0 = self.state0
state1 = self.state1
for word in tf.unstack(x, axis=1): # word: [b, 100]
# h1 = x*wxh+h0*whh
# out0: [b, 64]
out0, state0 = self.rnn_cell0(word, state0, training)
# out1: [b, 64]
out1, state1 = self.rnn_cell1(out0, state1, training)
# out: [b, 64] => [b, 1]
x = self.outlayer(out1)
# p(y is pos|x)
prob = tf.sigmoid(x)
return prob
def main():
units = 64
epochs = 4
model = MyRNN(units)
model.compile(optimizer=keras.optimizers.Adam(0.001),
loss=tf.losses.BinaryCrossentropy(),
metrics=['accuracy'])
model.fit(db_train, epochs=epochs, validation_data=db_test)
model.evaluate(db_test)
if __name__ == '__main__':
main()
Multi-layers
import os
import tensorflow as tf
import numpy as np
from tensorflow import keras
from tensorflow.keras import layers
tf.random.set_seed(22)
np.random.seed(22)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
assert tf.__version__.startswith('2.')
batchsz = 128
# the most frequest words
total_words = 10000 # 编码10000个单词
max_review_len = 80 # 句子长度80
embedding_len = 100
(x_train,
y_train), (x_test,
y_test) = keras.datasets.imdb.load_data(num_words=total_words)
# x_train:[b, 80]
# x_test: [b, 80]
x_train = keras.preprocessing.sequence.pad_sequences(x_train,
maxlen=max_review_len)
x_test = keras.preprocessing.sequence.pad_sequences(x_test,
maxlen=max_review_len)
db_train = tf.data.Dataset.from_tensor_slices((x_train, y_train))
# drop_remainder,丢弃最后一个大小不合适的batch
db_train = db_train.shuffle(1000).batch(batchsz, drop_remainder=True)
db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test))
db_test = db_test.batch(batchsz, drop_remainder=True)
print('x_train shape:', x_train.shape, tf.reduce_max(y_train),
tf.reduce_min(y_train))
print('x_test shape:', x_test.shape)
class MyRNN(keras.Model):
def __init__(self, units):
super(MyRNN, self).__init__()
# transform text to embedding representation
# [b, 80] => [b, 80, 100] # embedding_len=100表示一个单词为100的向量
self.embedding = layers.Embedding(total_words,
embedding_len,
input_length=max_review_len)
# [b, 80, 100] , h_dim: 64
self.rnn = keras.Sequential([
layers.SimpleRNN(units,
dropout=0.5,
return_sequences=True,
unroll=True),
layers.SimpleRNN(units, dropout=0.5, unroll=True)
])
# fc, [b, 80, 100] => [b, 64] => [b, 1] # 得到分类结果
self.outlayer = layers.Dense(1)
def call(self, inputs, training=None):
"""
net(x) net(x, training=True) :train mode
net(x, training=False): test
:param inputs: [b, 80]
:param training: 计算过程是train还是test
:return:
"""
# [b, 80]
x = inputs
# embedding: [b, 80] => [b, 80, 100]
x = self.embedding(x)
# rnn cell compute
# x: [b, 80, 100] => [b, 64]
x = self.rnn(x)
# out: [b, 64] => [b, 1]
x = self.outlayer(x)
# p(y is pos|x)
prob = tf.sigmoid(x)
return prob
def main():
units = 64
epochs = 4
model = MyRNN(units)
model.compile(optimizer=keras.optimizers.Adam(0.001),
loss=tf.losses.BinaryCrossentropy(),
metrics=['accuracy'])
model.fit(db_train, epochs=epochs, validation_data=db_test)
model.evaluate(db_test)
if __name__ == '__main__':
main()
RNN与情感分类问题实战-加载IMDB数据集的更多相关文章
- pytorch 加载mnist数据集报错not gzip file
利用pytorch加载mnist数据集的代码如下 import torchvision import torchvision.transforms as transforms from torch.u ...
- torchvision的理解和学习 加载常用数据集,对主流模型的调用.md
torchvision的理解和学习 加载常用数据集,对主流模型的调用 https://blog.csdn.net/tsq292978891/article/details/79403617 加载常用数 ...
- 科学计算三维可视化---TVTK管线与数据加载(数据集)
一:数据集 三维可视化的第一步是选用合适的数据结构来表示数据,TVTK提供了多种表示不同种类数据的数据集 (一)数据集--ImageData >>> from tvtk.api im ...
- Tensorflow之快速加载MNIST数据集
from tensorflow.examples.tutorials.mnist import input_data import tensorflow as tf def myprint(v): p ...
- Pytorch文本分类(imdb数据集),含DataLoader数据加载,最优模型保存
用pytorch进行文本分类,数据集为keras内置的imdb影评数据(二分类),代码包含六个部分(详见代码) 使用环境: pytorch:1.1.0 cuda:10.0 gpu:RTX2070 (1 ...
- [DeeplearningAI笔记]序列模型2.9情感分类
5.2自然语言处理 觉得有用的话,欢迎一起讨论相互学习~Follow Me 2.9 Sentiment classification 情感分类 情感分类任务简单来说是看一段文本,然后分辨这个人是否喜欢 ...
- JVM学习二:JVM之类加载器之加载分析
前面一遍,我们对类的加载有了一个整体的认识,而这一节我们细节分析一下类加载器的第一步,即:加载. 一.概念 类的加载指的是将类的.class文件中的二进制数据读入到内存中,将其放在运行时数据区的方法区 ...
- UIButton 加载网络图片
以后就可以 用这个分类 UIButton轻松加载网络图片了, UIButton+WebCache.h #import <UIKit/UIKit.h> @interface UIButt ...
- Pytorch加载并可视化FashionMNIST指定层(Udacity)
加载并可视化FashionMNIST 在这个notebook中,我们要加载并查看 Fashion-MNIST 数据库中的图像. 任何分类问题的第一步,都是查看你正在使用的数据集.这样你可以了解有关图像 ...
随机推荐
- 第四代增强 NEW BADI的定义及实现
NEW BADI 是在第四代增强框架下创建的BADI,是相对于第三代增强Classic Badi 而言的. 根据第四代增强的基本概念,所有显式增强Enhancement options 都必须放在增强 ...
- Luogu P1970 花匠 【线性Dp】 By cellur925
题目描述 Description 花匠栋栋种了一排花,每株花都有自己的高度.花儿越长越大,也越来越挤.栋栋决定把这排中的一部分花移走,将剩下的留在原地,使得剩下的花能有空间长大,同时,栋栋希望剩下的花 ...
- python爬虫爬取腾讯招聘信息 (静态爬虫)
环境: windows7,python3.4 代码:(亲测可正常执行) import requests from bs4 import BeautifulSoup from math import c ...
- Unix\Linux | 总结笔记 | 命令_ WC
wc[选项][参数] wc命令用来计算数字.利用wc指令我们可以计算文件的Byte数.字数或是列数,若不指定文件名称,或是所给予的文件名为“-”,则wc指令会从标准输入设备读取数据. -c或--byt ...
- Hdu 3605 Escape (最大流 + 缩点)
题目链接: Hdu 3605 Escape 题目描述: 有n个人要迁移到m个星球,每个星球有最大容量,每个人有喜欢的星球,问是否所有的人都能迁移成功? 解题思路: 正常情况下建图,不会爆内存,但是T ...
- 1.1.1最短路(Floyd、Dijstra、BellmanFord)
转载自hr_whisper大佬的博客 [ 一.Dijkstra 比较详细的迪杰斯特拉算法讲解传送门 Dijkstra单源最短路算法,即计算从起点出发到每个点的最短路.所以Dijkstra常常作为其他算 ...
- 数学 SCU 4436 Easy Math
题目传送门 /* 数学题:当有一个数开根号后是无理数,则No */ #include <cstdio> #include <algorithm> #include <cs ...
- Toasts官方教程
Toasts IN THIS DOCUMENT The Basics Positioning your Toast Creating a Custom Toast View 在其它线程中启动Toast ...
- Mybatis查询select操作
先看select标签的属性: 说几点: resultType和resultMap都是用来表示结果集的类型的,resultType用于简单的HashMap或者是简单的pojo对象,而resultSet是 ...
- sh/bash/csh/Tcsh/ksh/pdksh等shell本质区别
sh/bash/csh/Tcsh/ksh/pdksh等shell本质区别 1. Shell脚本的书写 在写Shell脚本时,往往第一行要注明用什么解释器来解释这个脚本. 如#!/bin/bash即用/ ...