深度学习之LSTM实现

LSTM之keras实现

import numpy as np
np.random.seed(2017)  #为了复现
from __future__ import print_function
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import LSTM, Activation, Dense
from keras.optimizers import Adam

(X_train, y_train), (X_test, y_test) = mnist.load_data()

#参数
#学习率
learning_rate = 0.001 
#迭代次数
epochs = 2
#每块训练样本数
batch_size = 128
#输入
n_input = 28
#步长
n_step = 28
#LSTM Cell
n_hidden = 128
#类别
n_classes = 10

#x标准化到0-1  y使用one-hot  输入 nxm的矩阵 每行m维切成n个输入
X_train = X_train.reshape(-1, n_step, n_input)/255.
X_test = X_test.reshape(-1, n_step, n_input)/255.

y_train = np_utils.to_categorical(y_train, num_classes=10)
y_test = np_utils.to_categorical(y_test, num_classes=10)

model = Sequential()
model.add(LSTM(n_hidden,
               batch_input_shape=(None, n_step, n_input),
               unroll=True))

model.add(Dense(n_classes))
model.add(Activation('softmax'))

adam = Adam(lr=learning_rate)
#显示模型细节
model.summary()
model.compile(optimizer=adam,
              loss='categorical_crossentropy',
              metrics=['accuracy'])

model.fit(X_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1, #0不显示 1显示
          validation_data=(X_test, y_test))

scores = model.evaluate(X_test, y_test, verbose=0)
print('LSTM test score:', scores[0]) #loss
print('LSTM test accuracy:', scores[1])

TensorFlow之LSTM

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# set random seed for comparing the two result calculations
tf.set_random_seed(1)

# this is data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

# hyperparameters
lr = 0.001
training_iters = 100000
batch_size = 128

n_inputs = 28   # MNIST data input (img shape: 28*28)
n_steps = 28    # time steps
n_hidden_units = 128   # neurons in hidden layer 隐藏神经元个数
n_classes = 10      # MNIST classes (0-9 digits)

# tf Graph input
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])

# Define weights
weights = {
    # (28, 128)
    'in': tf.Variable(tf.random_normal([n_inputs, n_hidden_units])),
    # (128, 10)
    'out': tf.Variable(tf.random_normal([n_hidden_units, n_classes]))
}
biases = {
    # (128, )
    'in': tf.Variable(tf.constant(0.1, shape=[n_hidden_units, ])),
    # (10, )
    'out': tf.Variable(tf.constant(0.1, shape=[n_classes, ]))
}


def RNN(X, weights, biases):
    # hidden layer for input to cell
    ########################################

    # transpose the inputs shape from
    # X ==> (128 batch * 28 steps, 28 inputs)
    X = tf.reshape(X, [-1, n_inputs])

    # into hidden
    # X_in = (128 batch * 28 steps, 128 hidden)
    X_in = tf.matmul(X, weights['in']) + biases['in']
    # X_in ==> (128 batch, 28 steps, 128 hidden)
    X_in = tf.reshape(X_in, [-1, n_steps, n_hidden_units])

    # cell
    ##########################################

    # basic LSTM Cell.
    cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units)
    # lstm cell is divided into two parts (c_state, h_state)
    init_state = cell.zero_state(batch_size, dtype=tf.float32)

    # You have 2 options for following step.
    # 1: tf.nn.rnn(cell, inputs);
    # 2: tf.nn.dynamic_rnn(cell, inputs).
    # If use option 1, you have to modified the shape of X_in, go and check out this:
    # https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py
    # In here, we go for option 2.
    # dynamic_rnn receive Tensor (batch, steps, inputs) or (steps, batch, inputs) as X_in.
    # Make sure the time_major is changed accordingly.
    outputs, final_state = tf.nn.dynamic_rnn(cell, X_in, initial_state=init_state, time_major=False)

    # hidden layer for output as the final results
    #############################################
    # results = tf.matmul(final_state[1], weights['out']) + biases['out']

    # # or
    # unpack to list [(batch, outputs)..] * steps #交换维度
    outputs = tf.unstack(tf.transpose(outputs, [1,0,2]))
    results = tf.matmul(outputs[-1], weights['out']) + biases['out']    # shape = (128, 10)

    return results


pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
train_op = tf.train.AdamOptimizer(lr).minimize(cost)

correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

with tf.Session() as sess:
    init = tf.global_variables_initializer()
    sess.run(init)
    step = 0
    while step * batch_size < training_iters:
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        batch_xs = batch_xs.reshape([batch_size, n_steps, n_inputs])
        sess.run([train_op], feed_dict={
            x: batch_xs,
            y: batch_ys,
        })
        if step % 20 == 0:
            print(sess.run(accuracy, feed_dict={
            x: batch_xs,
            y: batch_ys,
            }))
        step += 1