转自：https://blog.csdn.net/u012458963/article/details/74357802
RNN
首先了解了RNN，有很多的教程，这里大概贴几个网址
https://www.yunaitong.cn/understanding-lstm-networks.html
http://feisky.xyz/machine-learning/rnn/
还有莫烦的教程
我自己尝试着用keras写RNN的例子，参考了莫烦的教程，但是用莫烦的程序得到的结果特别不理想
然后就尝试着用开发者fchollet的例子
https://github.com/fchollet/keras/blob/8f4d6fc3fa6cd35a36de190a5e44ab4817cc68e8/examples/mnist_irnn.py
用f大神的例子运行速度特别慢，运行结果如图所示，结果也不理想
然后我看了下代码，代码用的是784个timestep，一个量一个量传的。
X_train = X_train.reshape(X_train.shape[0], -1, 1)
X_test = X_test.reshape(X_test.shape[0], -1, 1)- 1
- 2
于是我把输入进行了修改， 变成28个timestep, 每次输入的量是28个量
x_train = x_train.reshape(-1, 28, 28)
x_test = x_test.reshape(-1, 28, 28)- 1
- 2
这样运行的速度就快多了，但是运行效果还是不理想
我百思不得其解，然后我自己重新写代码，发现在f大神的代码中有learning rate, 有了LR，运行结果总是60~70%，当我去掉LR时，运行结果就在96%左右
附上代码
#!/usr/bin/python
# -*- coding:utf8 -*-
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.layers import SimpleRNN
from keras import initializers
from keras.optimizers import RMSprop
batch_size = 50
num_classes = 10
epochs = 100
hidden_units = 50
# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(-1, 28, 28)
x_test = x_test.reshape(-1, 28, 28)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print('Evaluate RNN...')
model = Sequential()
model.add(SimpleRNN(hidden_units,
kernel_initializer=initializers.RandomNormal(stddev=0.001),
recurrent_initializer=initializers.Identity(gain=1.0),
activation='relu',
input_shape=x_train.shape[1:]))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
rmsprop = RMSprop()
model.compile(loss='categorical_crossentropy',
optimizer=rmsprop,
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
scores = model.evaluate(x_test, y_test, verbose=0)
print('RNN test score:', scores[0])
print('RNN test accuracy:', scores[1])PhysioNet
下载了几篇文章