【转】python实现简单的LSTM

72 阅读 0 评论 48 点赞

我是靠谱客的博主自觉裙子，最近开发中收集的这篇文章主要介绍【转】python实现简单的LSTM，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

直接上代码：

""" 
@file: my_lstm.py
@Time: 2018/09/17
@Author:hnq
"""
import numpy
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.utils import np_utils
# fix random seed for reproducibility
numpy.random.seed(7)
# define the raw dataset
alphabet = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
# create mapping of characters to integers (0-25) and the reverse
char_to_int = dict((c, i) for i, c in enumerate(alphabet))
int_to_char = dict((i, c) for i, c in enumerate(alphabet))
# prepare the dataset of input to output pairs encoded as integers
seq_length = 3
dataX = []
dataY = []
for i in range(0, len(alphabet) - seq_length, 1):
    seq_in = alphabet[i:i + seq_length]
    seq_out = alphabet[i + seq_length]
    dataX.append([char_to_int[char] for char in seq_in])
    dataY.append(char_to_int[seq_out])
    print (seq_in, '->', seq_out)
# reshape X to be [samples, time steps, features]
X = numpy.reshape(dataX, (len(dataX), 1, seq_length))
# normalize
X = X / float(len(alphabet))
# one hot encode the output variable
y = np_utils.to_categorical(dataY)
# create and fit the model
model = Sequential()
model.add(LSTM(32, input_shape=(X.shape[1], X.shape[2])))
model.add(Dense(y.shape[1], activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X, y, nb_epoch=500, batch_size=1, verbose=2)
# summarize performance of the model
scores = model.evaluate(X, y, verbose=0)
print("Model Accuracy: %.2f%%" % (scores[1]*100))
# demonstrate some model predictions
for pattern in dataX:
    x = numpy.reshape(pattern, (1, 1, len(pattern)))
    x = x / float(len(alphabet))
    prediction = model.predict(x, verbose=0)
    index = numpy.argmax(prediction)
    result = int_to_char[index]
    seq_in = [int_to_char[value] for value in pattern]
    print (seq_in, "->", result)

输出：

ABC -> D
BCD -> E
CDE -> F
DEF -> G
EFG -> H
FGH -> I
GHI -> J
HIJ -> K
IJK -> L
JKL -> M
KLM -> N
LMN -> O
MNO -> P
NOP -> Q
OPQ -> R
PQR -> S
QRS -> T
RST -> U
STU -> V
TUV -> W
UVW -> X
VWX -> Y
WXY -> Z
D:Anacondalibsite-packagesipykernel_launcher.py:39: UserWarning: The `nb_epoch` argument in `fit` has been renamed `epochs`.
Epoch 1/500
 - 2s - loss: 3.2651 - acc: 0.0000e+00
Epoch 2/500
 - 0s - loss: 3.2527 - acc: 0.0435
……
……
……