请求的 tensorflow = float64_ref，实际 = float64

Question

我只是想让一个简单的 RNNCell 工作。这个简单的代码：

with tf.Session() as sess:
    x = tf.Variable(np.ones((2, 3)))
    tf.initialize_all_variables().run()
    out, state = BasicRNNCell(4)(x, x)

抛出以下错误：

Traceback (most recent call last):
  File "scrap.py", line 38, in <module>
    g, _ = tf.nn.rnn_cell.BasicRNNCell(2)(x, x)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/rnn_cell.py", line 199, in __call__
    output = self._activation(_linear([inputs, state], self._num_units, True))
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/rnn_cell.py", line 903, in _linear
    "Matrix", [total_arg_size, output_size], dtype=dtype)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 1022, in get_variable
    custom_getter=custom_getter)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 849, in get_variable
    custom_getter=custom_getter)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 345, in get_variable
    validate_shape=validate_shape)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 330, in _true_getter
    caching_device=caching_device, validate_shape=validate_shape)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 676, in _get_single_variable
    validate_shape=validate_shape)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/variables.py", line 215, in __init__
    dtype=dtype)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/variables.py", line 288, in _init_from_args
    initial_value(), name="initial_value", dtype=dtype)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 666, in <lambda>
    shape.as_list(), dtype=dtype, partition_info=partition_info)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/init_ops.py", line 280, in _initializer
    dtype, seed=seed)
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/ops/random_ops.py", line 232, in random_uniform
    minval = ops.convert_to_tensor(minval, dtype=dtype, name="min")
  File "/Users/ethan/env/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 671, in convert_to_tensor
    dtype.name, ret.dtype.name))
RuntimeError: min: Conversion function <function _constant_tensor_conversion_function at 0x112053c08> for type <type 'object'> returned incompatible dtype: requested = float64_ref, actual = float64

这是pip show tensorflow的输出：

Metadata-Version: 2.0 Name: tensorflow Version: 0.11.0rc1 Summary: TensorFlow helps the tensors flow Home-page: http://tensorflow.org/ Author: Google Inc. Author-email: opensource@google.com Installer: pip License: Apache 2.0 Location: /Users/ethan/env/lib/python2.7/site-packages Requires: mock, protobuf, numpy, wheel, six Classifiers: Development Status :: 4 - Beta Intended Audience :: Developers Intended Audience :: Education Intended Audience :: Science/Research License :: OSI Approved :: Apache Software License Programming Language :: Python :: 2.7 Topic :: Scientific/Engineering :: Mathematics Topic :: Software Development :: Libraries :: Python Modules Topic :: Software Development :: Libraries Entry-points: [console_scripts] tensorboard = tensorflow.tensorboard.tensorboard:main

谢谢！

Answer 1

我认为这是 Tensorflow 中的一个错误，我邀请您 open an issue on GitHub。

要解决此问题，您可以使用 tf.identity 创建 float64_ref 而不是 float64 x 并将此值作为 inputs 传递参数.

import tensorflow as tf
import numpy as np

with tf.Session() as sess:
    x = tf.Variable(np.ones((2, 3)))
    sess.run(tf.initialize_all_variables())
    out, state = tf.nn.rnn_cell.BasicRNNCell(4)(tf.identity(x), x)

Answer 2

在 TensorFlow 中，class 张量的 dtype 为 float64_ref，class 变量的 dtype 为 float64。而 BasicRNNCell 需要一个 Tensor 而不是 Variable 作为输入。在你的代码中， x = tf.Variable(...) 应该改成 x = tf.convert_to_tensor(...)

请求的 tensorflow = float64_ref，实际 = float64

tensorflow requested = float64_ref, actual = float64

type-conversion

tensorflow

recurrent-neural-network