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:\Anaconda\lib\site-packages\ipykernel_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
……
……
……