Recurrent Neural Networks Tutorial

最新推荐文章于 2023-09-22 01:28:55 发布

原创最新推荐文章于 2023-09-22 01:28:55 发布 · 594 阅读

0 ·

本内容遵循CC 4.0 BY-SA版权协议

收录于

机器学习

本文介绍如何使用Keras深度学习库构建一个时间序列预测模型，包括数据准备、模型搭建、训练及评估等步骤，并提供完整的代码实现。

http://www.tuicool.com/articles/nQBjUj

# -*- coding: utf-8 -*-
"""
Created on Sat Jun 11 15:30:33 2016

@author: Shemmy
"""
from keras.models import Sequential
from keras.layers.core import TimeDistributedDense, Dense, Activation, Dropout
from keras.layers.recurrent import GRU, LSTM
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from keras.optimizers import RMSprop
import numpy as np

def _load_data(data, steps = 4):
    docX, docY = [], []
    for i in range(0, data.shape[0]-steps):
        docX.append(data[i:i+steps,:])
        docY.append(data[i+steps,:])
    return np.array(docX), np.array(docY)

def train_test_split(data, test_size=0.15):
    #    This just splits data to training and testing parts
    X,Y = _load_data(data)
    ntrn = round(X.shape[0] * (1 - test_size))
    X_train, Y_train = X[0:ntrn], Y[0:ntrn]
    X_test, Y_test = X[ntrn:],Y[ntrn:]
    return (X_train, Y_train), (X_test, Y_test)

np.random.seed(0) # For reproducability
data = np.arange(5).reshape((5,1))
for i in xrange(10):
    data = np.append(data, data, axis=0)
(X_train, y_train), (X_test, y_test) = train_test_split(np.flipud(data)) # retrieve data
print "Data loaded."

in_out_neurons = 1
hidden_neurons = 10

model = Sequential()
model.add(GRU(hidden_neurons, input_dim=in_out_neurons, return_sequences=False))
model.add(Dropout(0.2))
model.add(Dense(in_out_neurons))
model.add(Activation("linear"))
model.compile(loss="mean_squared_error", optimizer="rmsprop")
print "Model compiled."

model.fit(X_train, y_train, batch_size=10, nb_epoch=10, validation_split=0.1)
predicted = model.predict(X_test)
print np.sqrt(((predicted - y_test) ** 2).mean(axis=0)).mean()
print predicted

https://github.com/fchollet/keras/issues/1029