TensorFlow - 'Split' Op 的输入'split_dim' 的 float32 类型与预期的 int32 类型不匹配

Question

我在 ubuntu 16.04 LTS 上使用 pip 安装了 tensorflow，在运行此代码 https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py 时出现此错误

Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes. 
Extracting /tmp/data/train-images-idx3-ubyte.gz 
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes. Extracting /tmp/data/train-labels-idx1-ubyte.gz 
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes. 
Extracting /tmp/data/t10k-images-idx3-ubyte.gz
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes. 
Extracting /tmp/data/t10k-labels-idx1-ubyte.gz 
Traceback (most recent call last): 
    File "deep.py", line 71, in <module>
        pred = RNN(x, weights, biases)   
    File "deep.py", line 60, in RNN
        x = tf.split(x, n_steps, 0)   
    File "/home/newuser/.local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1234, in split
        name=name)   
    File "/home/newuser/.local/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 3241, in _split
    num_split=num_split, name=name)   
    File "/home/newuser/.local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 508, in apply_op
    (prefix, dtypes.as_dtype(input_arg.type).name)) 
TypeError: Input 'split_dim' of 'Split' Op has type float32 that does not match expected type of int32.

Answer 1

您使用的是较旧版本的 Tensorflow，需要更新到 Tensorflow v0.12.0 或更高版本。您收到的错误表明您的 tf.split 函数中的 split_dim 值需要一个整数，但正在接收 float32 类型的张量 x。

这是因为在 Tensorflow 版本

x = tf.split(0, n_steps, x) # tf.split(axis, num_or_size_splits, value)

您正在使用的教程是为 > 0.12.0 版本编写的，该版本已更改为与 Numpy 的拆分语法一致：

x = tf.split(x, n_steps, 0) # tf.split(value, num_or_size_splits, axis)

查看更新日志了解详情： https://github.com/tensorflow/tensorflow/blob/64edd34ce69b4a8033af5d217cb8894105297d8a/RELEASE.md

Answer 2

是因为参数顺序变了

您可以在此处查看问题：https://github.com/tensorflow/tensorflow/issues/6501