我正在尝试执行以下操作
state[0,:] = state[0,:].assign( 0.9*prev_state + 0.1*( tf.matmul(inputs, weights) + biases ) )
for i in xrange(1,BATCH_SIZE):
state[i,:] = state[i,:].assign( 0.9*state[i-1,:] + 0.1*( tf.matmul(inputs, weights) + biases ) )
prev_state = prev_state.assign( state[BATCH_SIZE-1,:] )
带
state = tf.Variable(tf.zeros([BATCH_SIZE, HIDDEN_1]), name='inner_state')
prev_state = tf.Variable(tf.zeros([HIDDEN_1]), name='previous_inner_state')
作为this question的后续行动。我收到Tensor
没有assign
方法的错误。
在assign
张量的切片上调用Variable
方法的正确方法是什么?
完整的当前代码:
import tensorflow as tf
import math
import numpy as np
INPUTS = 10
HIDDEN_1 = 20
BATCH_SIZE = 3
def create_graph(inputs, state, prev_state):
with tf.name_scope('h1'):
weights = tf.Variable(
tf.truncated_normal([INPUTS, HIDDEN_1],
stddev=1.0 / math.sqrt(float(INPUTS))),
name='weights')
biases = tf.Variable(tf.zeros([HIDDEN_1]), name='biases')
updated_state = tf.scatter_update(state, [0], 0.9 * prev_state + 0.1 * (tf.matmul(inputs[0,:], weights) + biases))
for i in xrange(1, BATCH_SIZE):
updated_state = tf.scatter_update(
updated_state, [i], 0.9 * updated_state[i-1, :] + 0.1 * (tf.matmul(inputs[i,:], weights) + biases))
prev_state = prev_state.assign(updated_state[BATCH_SIZE-1, :])
output = tf.nn.relu(updated_state)
return output
def data_iter():
while True:
idxs = np.random.rand(BATCH_SIZE, INPUTS)
yield idxs
with tf.Graph().as_default():
inputs = tf.placeholder(tf.float32, shape=(BATCH_SIZE, INPUTS))
state = tf.Variable(tf.zeros([BATCH_SIZE, HIDDEN_1]), name='inner_state')
prev_state = tf.Variable(tf.zeros([HIDDEN_1]), name='previous_inner_state')
output = create_graph(inputs, state, prev_state)
sess = tf.Session()
# Run the Op to initialize the variables.
init = tf.initialize_all_variables()
sess.run(init)
iter_ = data_iter()
for i in xrange(0, 2):
print ("iteration: ",i)
input_data = iter_.next()
out = sess.run(output, feed_dict={ inputs: input_data})
答案 0 :(得分:3)
使用tf.scatter_update()
,tf.scatter_add()
和tf.scatter_sub()
操作,Tensorflow Variable
对象对更新切片的支持有限。这些操作中的每一个都允许您指定变量,切片索引的向量(表示变量的第0维中的索引,表示要变异的连续切片)和值的张量(表示要应用于的新值)变量,在相应的切片索引处。)
要更新变量的单行,您可以使用tf.scatter_update()
。例如,要更新state
的第0行,您可以执行以下操作:
updated_state = tf.scatter_update(
state, [0], 0.9 * prev_state + 0.1 * (tf.matmul(inputs, weights) + biases))
要链接多个更新,您可以使用从updated_state
返回的可变tf.scatter_update()
张量:
for i in xrange(1, BATCH_SIZE):
updated_state = tf.scatter_update(
updated_state, [i], 0.9 * updated_state[i-1, :] + ...)
prev_state = prev_state.assign(updated_state[BATCH_SIZE-1, :])
最后,您可以评估生成的updated_state.op
以将所有更新应用于state
:
sess.run(updated_state.op) # or `sess.run(updated_state)` to fetch the result
PS。您可能会发现使用tf.scan()
计算中间状态更有效,并且只是在变量中实现prev_state
。