import numpy as np
import tensorflow as tf
import input_data
import matplotlib.pyplot as plt
def _RNN(_X, _W, _b, _nsteps, _name, diminput=28, dimhidden=128):
# 1. Permute input from [batchsize, nsteps, diminput]
# => [nsteps, batchsize, diminput]
_X = tf.transpose(_X, [1, 0, 2])
# 2. Reshape input to [nsteps*batchsize, diminput]
_X = tf.reshape(_X, [-1, diminput])
# 3. Input layer => Hidden layer
_H = tf.matmul(_X, _W['hidden']) + _b['hidden']
# 4. Splite data to 'nsteps' chunks. An i-th chunck indicates i-th batch data
_Hsplit = tf.split(axis=0, num_or_size_splits=_nsteps, value=_H)
# 5. Get LSTM's final output (_LSTM_O) and state (_LSTM_S)
# Both _LSTM_O and _LSTM_S consist of 'batchsize' elements
# Only _LSTM_O will be used to predict the output.
with tf.variable_scope(_name, reuse=tf.AUTO_REUSE) as scope:
# scope.reuse_variables()
# lstm_cell = tf.contrib.rnn.BasicLSTMCell(lstm_size)
# outputs, final_state = tf.nn.dynamic_rnn(lstm_cell, inputs, dtype=tf.float32)
# lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(dimhidden, forget_bias=1.0)
lstm_cell = tf.contrib.rnn.BasicLSTMCell(dimhidden, forget_bias=1.0)
# _LSTM_O, _LSTM_S = tf.nn.rnn(lstm_cell, _Hsplit, dtype=tf.float32)
_LSTM_O, _LSTM_S = tf.contrib.rnn.static_rnn(lstm_cell, _Hsplit, dtype=tf.float32)
# 6. Output
_O = tf.matmul(_LSTM_O[-1], _W['out']) + _b['out']
# Return!
return {
'X': _X, 'H': _H, 'Hsplit': _Hsplit,
'LSTM_O': _LSTM_O, 'LSTM_S': _LSTM_S, 'O': _O
}
def study_rnn():
# mnist = input_data.read_data_sets('./objects_data/mnist', one_hot=True)
mnist = input_data.read_data_sets('./objects_data/fashion-mnist-master/fashion_mnist_data', one_hot=True)
trainimgs, trainlabels, testimgs, testlabels = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
ntrain, ntest, dim, nclasses = trainimgs.shape[0], testimgs.shape[0], trainimgs.shape[1], trainlabels.shape[1]
print("MNIST loaded")
diminput = 28
dimhidden = 128
dimoutput = nclasses
nsteps = 28
n_layers = 1
weights = {
'hidden': tf.Variable(tf.random_normal([diminput, dimhidden])),
'out': tf.Variable(tf.random_normal([dimhidden, dimoutput]))
}
biases = {
'hidden': tf.Variable(tf.random_normal([dimhidden])),
'out': tf.Variable(tf.random_normal([dimoutput]))
}
learning_rate = 0.001
x = tf.placeholder("float", [None, nsteps, diminput])
y = tf.placeholder("float", [None, dimoutput])
# rnn中的中间状态变量,包含cell 的状态(c_t)和每个cell 的输出状态(h_t) 对应lstm的输出公式[ht=o*tanh(ct)]
# 本例中的多层RNN中,每一个CELL中的状态数目相等,因此输入状态变量是2*n_hidden*n_layers],实际上是可以不相等的
# 另外,可以提供初始状态,也可以不提供,让tf自动初始化
istate = tf.placeholder("float32", [None, 2 * dimhidden * n_layers])
myrnn = _RNN(x, weights, biases, nsteps, 'basic')
pred = myrnn['O']
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optm = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) # Adam Optimizer
accr = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)), tf.float32))
init = tf.global_variables_initializer()
print("Network Ready!")
training_epochs = 10
batch_size = 16
display_step = 1
sess = tf.Session()
sess.run(init)
print("Start optimization")
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples/batch_size)
# total_batch = 100
# Loop over all batches
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
batch_xs = batch_xs.reshape((batch_size, nsteps, diminput))
# Fit training using batch data
feeds = {x: batch_xs, y: batch_ys}
sess.run(optm, feed_dict=feeds)
# Compute average loss
avg_cost += sess.run(cost, feed_dict=feeds) / total_batch
# Display logs per epoch step
if epoch % display_step == 0:
print("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
feeds = {x: batch_xs, y: batch_ys}
train_acc = sess.run(accr, feed_dict=feeds)
print(" Training accuracy: %.3f" % (train_acc))
testimgs = testimgs.reshape((ntest, nsteps, diminput))
feeds = {x: testimgs, y: testlabels, istate: np.zeros((ntest, 2 * dimhidden))}
test_acc = sess.run(accr, feed_dict=feeds)
print(" Test accuracy: %.3f" % (test_acc))
print("Optimization Finished.")
if __name__ == '__main__':
study_rnn()
最近在学TensorFlow但无奈电脑是CUDA8.0,所以只好用1.4版本了
另外input_data.py代码为:
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import gzip
import os
import tempfile
import numpy
from six.moves import urllib
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets
这里也有一份RNN写的不错的,附上链接:
http://blog.sina.com.cn/s/blog_4b0020f30102wv4l.html