以下是代码(from here):
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.python.ops import rnn, rnn_cell
mnist = input_data.read_data_sets("/tmp/data/", one_hot = True)
hm_epochs = 3
n_classes = 10
batch_size = 128
chunk_size = 28
n_chunks = 28
rnn_size = 128
x = tf.placeholder('float', [None, n_chunks,chunk_size])
y = tf.placeholder('float')
def recurrent_neural_network(x):
layer = {'weights':tf.Variable(tf.random_normal([rnn_size,n_classes])),
'biases':tf.Variable(tf.random_normal([n_classes]))}
x = tf.transpose(x, [1,0,2])
x = tf.reshape(x, [-1, chunk_size])
x = tf.split(0, n_chunks, x)
lstm_cell = rnn_cell.BasicLSTMCell(rnn_size,state_is_tuple=True)
outputs, states = rnn.rnn(lstm_cell, x, dtype=tf.float32)
output = tf.matmul(outputs[-1],layer['weights']) + layer['biases']
return output
def train_neural_network(x):
prediction = recurrent_neural_network(x)
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
optimizer = tf.train.AdamOptimizer().minimize(cost)
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
for epoch in range(hm_epochs):
epoch_loss = 0
for _ in range(int(mnist.train.num_examples/batch_size)):
epoch_x, epoch_y = mnist.train.next_batch(batch_size)
epoch_x = epoch_x.reshape((batch_size,n_chunks,chunk_size))
_, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y: epoch_y})
epoch_loss += c
print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Accuracy:',accuracy.eval({x:mnist.test.images.reshape((-1, n_chunks, chunk_size)), y:mnist.test.labels}))
train_neural_network(x)
我有问题理解x = tf.split(0, n_chunks, x)
,更具体地说是第三个参数(x
- 输入)。到documenation,这应该是轴......但那不可能,对吧?不是x
一维吗?
我道歉,如果它是微不足道的,我是初学者,并且无法获得它。也许它只是形式,但如果是,我不明白它是如何运作的......
答案 0 :(得分:1)
通过记录,这应该是轴......但那不可能,对吧?
从tensorflow 1.0开始,tf.split
的第一个参数不是轴,但我假设代码是使用旧版本编写的,其中第一个参数确实是轴。
不是一维吗?
x
不是一维的。在致电tf.split
之前,使用此声明将x
从3维转换为2维:
x = tf.reshape(x, [-1, chunk_size])
该语句将x
重新整形为具有两个维度的张量:第二维的大小为chunk_size
,推断出第一维的大小(即-1
表示的大小这里)。