Question

import tensorflow as tf

B = 3
D = 4
T = 5

tf.reset_default_graph()

xs = tf.placeholder(shape=[T, B, D], dtype=tf.float32)

with tf.variable_scope("RNN"):
    GRUcell = tf.contrib.rnn.GRUCell(num_units = D)
    cell = tf.contrib.rnn.MultiRNNCell([GRUcell]) 

    output_ta = tf.TensorArray(size=T, dtype=tf.float32)
    input_ta = tf.TensorArray(size=T, dtype=tf.float32)
    input_ta.unstack(xs)

    def body(time, output_ta_t, state):
        xt = input_ta.read(time)
        new_output, new_state = cell(xt, state)
        output_ta_t.write(time, new_output)
        return (time+1, output_ta_t, new_state)

    def condition(time, output, state):
        return time < T

    time = 0
    state = cell.zero_state(B, tf.float32)

    time_final, output_ta_final, state_final = tf.while_loop(
          cond=condition,
          body=body,
          loop_vars=(time, output_ta, state))

    output_final = output_ta_final.stack()

我跑了

x = np.random.normal(size=(T, B, D))
with tf.Session() as sess:
    tf.global_variables_initializer().run()
    output_final_, state_final_ = sess.run(fetches = [output_final, state_final], feed_dict = {xs:x})

我想了解如何在循环时与TensorFlow相关地正确使用TensorArray。在上面的示例中，我收到以下错误：

InvalidArgumentError: TensorArray RNN/TensorArray_1_21: Could not read from TensorArray index 0 because it has not yet been written to.

我不明白这个“无法读取TensorArray索引0”。我想我通过unstack写入TensorArray input_ta，并在while主体中写入output_ta。我做错了什么？谢谢你的帮助。

Answer 1

解决方案是改变

input_ta.unstack(xs)

到

input_ta = input_ta.unstack(xs)

并同样改变

output_ta_t.write(time, new_output)

到

output_ta_t = output_ta_t.write(time, new_output)

通过这两项更改，代码按预期运行。

使用TensorArray进行TensorFlow while循环

1 个答案: