深度学习2.0-40.LSTM原理及实战

文章目录

1.LSTM原理
2.LSTM的实战

1.LSTM原理

2.LSTM的实战

import osos.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
import numpy as np
from tensorflow import keras
from tensorflow.keras import layerstf.random.set_seed(22)
np.random.seed(22)
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)# 修改两处self.state0与self.rnn_cell0
class MyRNN(keras.Model):def __init__(self, units):super(MyRNN, self).__init__()# [b, 64]self.state0 = [tf.zeros([batchsz, units]), tf.zeros([batchsz, units])]self.state1 = [tf.zeros([batchsz, units]), 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, cell3self.rnn_cell0 = layers.LSTMCell(units, dropout=0.5)self.rnn_cell1 = layers.LSTMCell(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 modenet(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.state0state1 = self.state1for 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 probdef main():units = 64epochs = 4import timet0 = time.time()model = MyRNN(units)model.compile(optimizer=keras.optimizers.Adam(0.001),loss=tf.losses.BinaryCrossentropy(),metrics=['accuracy'],experimental_run_tf_function=False)model.fit(db_train, epochs=epochs, validation_data=db_test)model.evaluate(db_test)t1 = time.time()# 64.3 seconds, 83.4%print('total time cost:', t1 - t0)if __name__ == '__main__':main()

import osos.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
import numpy as np
from tensorflow import keras
from tensorflow.keras import layerstf.random.set_seed(22)
np.random.seed(22)
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__()# 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: 64self.rnn = keras.Sequential([layers.LSTM(units, dropout=0.5, return_sequences=True, unroll=True),layers.LSTM(units, dropout=0.5, unroll=True)])# 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 modenet(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# 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 probdef main():units = 64epochs = 4import timet0 = time.time()model = MyRNN(units)model.compile(optimizer=keras.optimizers.Adam(0.001),loss=tf.losses.BinaryCrossentropy(),metrics=['accuracy'],experimental_run_tf_function=False)model.fit(db_train, epochs=epochs, validation_data=db_test)model.evaluate(db_test)t1 = time.time()# 69.3 secnods, 83%print('total time cost:', t1 - t0)if __name__ == '__main__':main()

深度学习2.0-40.LSTM原理及实战相关推荐

[深度学习] Pytorch中RNN/LSTM 模型小结
目录一 Liner 二 RNN 三 LSTM 四 LSTM 代码例子概念介绍可以参考:[深度学习]理解RNN, GRU, LSTM 网络 Pytorch中所有模型分为构造参数和输入和输出构造参数两 ...
深度学习笔记（40） YOLO
深度学习笔记(40) YOLO 1. YOLO对象检测算法 2. 构造训练集 3. 预测 3. 非极大值抑制 1. YOLO对象检测算法之前已经学到对象检测算法的大部分组件: 博文组件作用深度 ...
深度学习时间序列预测：LSTM算法构建时间序列单变量模型预测大气压（ air pressure）+代码实战
深度学习时间序列预测:LSTM算法构建时间序列单变量模型预测大气压( air pressure)+代码实战长短期记忆(Long short-term memory, LSTM)是一种特殊的RNN,主 ...
深度学习时间序列预测：LSTM算法构建时间序列单变量模型预测空气质量（PM2.5）+代码实战
深度学习时间序列预测:LSTM算法构建时间序列单变量模型预测空气质量(PM2.5)+代码实战 # 导入需要的包和函数: from __future__ import print_function im ...
浅谈深度学习：基于对LSTM项目`LSTM Neural Network for Time Series Prediction`的理解与回顾
浅谈深度学习:基于对LSTM项目LSTM Neural Network for Time Series Prediction的理解与回顾#### 总包含文章: 一个完整的机器学习模型的流程浅谈深度学 ...
halcon 深度学习标注_HALCON深度学习工具0.4 早鸟版发布了
原标题:HALCON深度学习工具0.4 早鸟版发布了 HALOCN深度学习工具在整个深度学习过程中扮演着重要的作用,而且在将来将扮演更重要的辅助作用,大大加快深度学习的开发流程,目前发布版本工具的主要 ...
halcon显示坐标_HALCON深度学习工具0.4 早鸟版发布了
HALOCN深度学习工具在整个深度学习过程中扮演着重要的作用,而且在将来将扮演更重要的辅助作用,大大加快深度学习的开发流程,目前发布版本工具的主要作用是图像数据处理和目标检测和分类中的标注. 标注训练 ...
系统学习深度学习（六） --LSTM总结
转自:http://blog.csdn.net/shincling/article/details/49362161 1. 概念: Long short-termmemory (LSTM)is a r ...
【深度学习之美】LSTM长短记，长序依赖可追忆（入门系列之十四）
14.1 遗忘是件好事还是坏事? 如果我问你,遗忘,是件好事,还是坏事? 或许你会说,当然是件坏事啊,我可羡慕记忆力好的人了. 可我要告诉你,如果你到现在还记得,两岁时,隔壁家的小女孩"横刀 ...
序列学习——RNN网络之 LSTM 原理
文章目录引入发展史 LSTMs 是什么短期记忆长期记忆 RNN 的局限 LSTM 网络详解符号约定 LSTM 网络分解其他 LSTM 网络整体模型引入所谓序列学习,就是输出不单单取决 ...

深度学习2.0-40.LSTM原理及实战

文章目录

1.LSTM原理

2.LSTM的实战

深度学习2.0-40.LSTM原理及实战相关推荐

最新文章

热门文章