版权声明:本文为业余狙击手原创文章,欢迎阅读,欢迎转载,转载请注明出处,谢谢。 https://blog.csdn.net/sxlsxl119/article/details/85157051
点击获取基于RNN&LSTM的MNIST手写字体识别源代码(GitHub)
这篇文章就不说RNN和LSTM的原理了,现在网上这类文章铺天盖地的。在这里把实际代码跑一下,同时对代码加了一些注释,并看一下执行效果,主要是通过实际代码加深对RNN和LSTM的理解。
一,基于RNN的MNIST手写字体识别
1.1 代码
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#设置随机种子用于比较两个计算结果
tf.set_random_seed(1)
# 加载数据
mnist = input_data.read_data_sets("E:\sxl_Programs\Python\MNIST_data\MNIST_data", one_hot=True)
# 超参数
lr = 0.0001 # 学习率
training_iters = 5000 # 训练轮数
batch_size = 200
n_inputs = 28 # MNIST data input (img shape: 28*28)
n_steps = 28 # time steps
n_hidden_units = 160 # neurons in hidden layer
n_classes = 10 # MNIST classes (0-9 digits)
# 输入输出
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])
# 权重
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.
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
else:
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
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) #预测
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y)) #损失函数
train_op = tf.train.AdamOptimizer(lr).minimize(cost) #优化器
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) #正确率
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) #正确率均值
with tf.Session() as sess:
# tf.initialize_all_variables() no long valid from
init = tf.global_variables_initializer()
sess.run(init)
step = 0
while step < 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})
step += 1
if step % 20 == 0:
train_acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys})
# print(" Iter%d,Train accuracy: %.3f" % (step,train_acc))
test_totalAccuracy = 0.0
irange = int(mnist.test.labels.shape[0] / batch_size) #数据集共有多少个batch_size
for i in range(irange):
test_batch_xs, test_batch_ys = mnist.test.next_batch(batch_size)
test_batch_xs = test_batch_xs.reshape([batch_size, n_steps, n_inputs])
feeds = {x: test_batch_xs, y: test_batch_ys}
test_acc = sess.run(accuracy, feed_dict=feeds)
test_totalAccuracy += test_acc
test_totalAccuracy = test_totalAccuracy / (irange)
print(" Iter%d,Train accuracy: %.3f,Test accuracy: %.3f" % (step, train_acc, test_totalAccuracy))
1.2 结果
迭代次数没有完全跑完...
二,基于LSTM的MNIST手写字体识别
2.1 代码
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#重置default graph计算图以及nodes节点
tf.reset_default_graph()
# 超参数
learning_rate = 0.01 # 学习率
n_steps = 28 # LSTM 展开步数(时序持续长度)
n_inputs = 28 # 输入节点数
n_hiddens = 64 # 隐层节点数
n_layers = 2 # LSTM layer 层数
n_classes = 10 # 输出节点数(分类数目)
# 加载数据
mnist = input_data.read_data_sets("E:\sxl_Programs\Python\MNIST_data\MNIST_data", one_hot=True)
test_x = mnist.test.images
test_y = mnist.test.labels
# tensor placeholder
with tf.name_scope('inputs'):
x = tf.placeholder(tf.float32, [None, n_steps * n_inputs], name='x_input') # 输入
y = tf.placeholder(tf.float32, [None, n_classes], name='y_input') # 输出
keep_prob = tf.placeholder(tf.float32, name='keep_prob_input') # 保持多少不被 dropout
batch_size = tf.placeholder(tf.int32, [], name='batch_size_input') # 批大小
# weights and biases
with tf.name_scope('weights'):
Weights = tf.Variable(tf.truncated_normal([n_hiddens, n_classes],stddev=0.1), dtype=tf.float32, name='W')
tf.summary.histogram('output_layer_weights', Weights)
with tf.name_scope('biases'):
biases = tf.Variable(tf.random_normal([n_classes]), name='b')
tf.summary.histogram('output_layer_biases', biases)
# RNN structure
def RNN_LSTM(x, Weights, biases):
# RNN 输入 reshape
x = tf.reshape(x, [-1, n_steps, n_inputs])
# 定义 LSTM cell
# cell 中的 dropout
def attn_cell():
lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hiddens)
with tf.name_scope('lstm_dropout'):
return tf.contrib.rnn.DropoutWrapper(lstm_cell, output_keep_prob=keep_prob)
# attn_cell = tf.contrib.rnn.DropoutWrapper(lstm_cell, output_keep_prob=keep_prob)
# 实现多层 LSTM
# [attn_cell() for _ in range(n_layers)]
enc_cells = []
for i in range(0, n_layers):
enc_cells.append(attn_cell())
with tf.name_scope('lstm_cells_layers'):
mlstm_cell = tf.contrib.rnn.MultiRNNCell(enc_cells, state_is_tuple=True)
# 全零初始化 state
_init_state = mlstm_cell.zero_state(batch_size, dtype=tf.float32)
# dynamic_rnn 运行网络
outputs, states = tf.nn.dynamic_rnn(mlstm_cell, x, initial_state=_init_state, dtype=tf.float32, time_major=False)
# 输出
#return tf.matmul(outputs[:,-1,:], Weights) + biases
return tf.nn.softmax(tf.matmul(outputs[:,-1,:], Weights) + biases)
with tf.name_scope('output_layer'):
pred = RNN_LSTM(x, Weights, biases)
tf.summary.histogram('outputs', pred)
# 损失函数
with tf.name_scope('loss'):
#cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
cost = tf.reduce_mean(-tf.reduce_sum(y * tf.log(pred),reduction_indices=[1]))
tf.summary.scalar('loss', cost)
# 优化器
with tf.name_scope('train'):
train_op = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
# accuarcy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
#准确率
with tf.name_scope('accuracy'):
accuracy = tf.metrics.accuracy(labels=tf.argmax(y, axis=1), predictions=tf.argmax(pred, axis=1))[1]
tf.summary.scalar('accuracy', accuracy)
merged = tf.summary.merge_all()
init = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
with tf.Session() as sess:
sess.run(init)
train_writer = tf.summary.FileWriter("E://logs//train",sess.graph)
test_writer = tf.summary.FileWriter("E://logs//test",sess.graph)
# training
step = 1
for i in range(10000):
_batch_size = 128
batch_x, batch_y = mnist.train.next_batch(_batch_size)
sess.run(train_op, feed_dict={x:batch_x, y:batch_y, keep_prob:0.5, batch_size:_batch_size})
if (i + 1) % 100 == 0:
loss = sess.run(cost, feed_dict={x:batch_x, y:batch_y, keep_prob:1.0, batch_size:_batch_size})
acc = sess.run(accuracy, feed_dict={x:batch_x, y:batch_y, keep_prob:1.0, batch_size:_batch_size})
print('Iter: %d' % ((i+1)), '| train loss: %.6f' % loss, '| train accuracy: %.6f' % acc)
train_result = sess.run(merged, feed_dict={x:batch_x, y:batch_y, keep_prob:1.0, batch_size:_batch_size})
test_result = sess.run(merged, feed_dict={x:test_x, y:test_y, keep_prob:1.0, batch_size:test_x.shape[0]})
train_writer.add_summary(train_result,i+1)
test_writer.add_summary(test_result,i+1)
print("Optimization Finished!")
# prediction
print("Testing Accuracy:", sess.run(accuracy, feed_dict={x:test_x, y:test_y, keep_prob:1.0, batch_size:test_x.shape[0]}))