Question

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})

Answer 1

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。

在tf.Variable张量切片上赋值

1 个答案: