InvalidArgumentError: 无法计算 Sub 作为输入 #1（从零开始）应该是一个 uint8 张量，但它是一个浮点张量 [Op:Sub]

Question

题

请帮助了解错误原因以及如何解决。

代码

import tensorflow as tf
import numpy as np

fashion_mnist = tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()
x_full = np.concatenate((x_train, x_test), axis=0)

layer = tf.keras.layers.experimental.preprocessing.Normalization()
layer.adapt(x_full)
layer(x_train)

错误

---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-16-699c47b6db55> in <module>
----> 1 ds = layer(x_train)

~/conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
    966           with base_layer_utils.autocast_context_manager(
    967               self._compute_dtype):
--> 968             outputs = self.call(cast_inputs, *args, **kwargs)
    969           self._handle_activity_regularization(inputs, outputs)
    970           self._set_mask_metadata(inputs, outputs, input_masks)

~/conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/keras/layers/preprocessing/normalization.py in call(self, inputs)
    109     mean = array_ops.reshape(self.mean, self._broadcast_shape)
    110     variance = array_ops.reshape(self.variance, self._broadcast_shape)
--> 111     return (inputs - mean) / math_ops.sqrt(variance)
    112 
    113   def compute_output_shape(self, input_shape):

~/conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/ops/math_ops.py in binary_op_wrapper(x, y)
    982     with ops.name_scope(None, op_name, [x, y]) as name:
    983       if isinstance(x, ops.Tensor) and isinstance(y, ops.Tensor):
--> 984         return func(x, y, name=name)
    985       elif not isinstance(y, sparse_tensor.SparseTensor):
    986         try:

~/conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py in sub(x, y, name)
  10098         pass  # Add nodes to the TensorFlow graph.
  10099     except _core._NotOkStatusException as e:
> 10100       _ops.raise_from_not_ok_status(e, name)
  10101   # Add nodes to the TensorFlow graph.
  10102   _, _, _op, _outputs = _op_def_library._apply_op_helper(

~/conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in raise_from_not_ok_status(e, name)
   6651   message = e.message + (" name: " + name if name is not None else "")
   6652   # pylint: disable=protected-access
-> 6653   six.raise_from(core._status_to_exception(e.code, message), None)
   6654   # pylint: enable=protected-access
   6655 

~/conda/envs/tensorflow/lib/python3.7/site-packages/six.py in raise_from(value, from_value)

InvalidArgumentError: cannot compute Sub as input #1(zero-based) was expected to be a uint8 tensor but is a float tensor [Op:Sub]

尝试

试过 dtype arg 但同样的错误。

layer = tf.keras.layers.experimental.preprocessing.Normalization(dtype='float32')

除以 1.0 解决了问题，但不确定原始原因。

x_full = np.concatenate((x_train, x_test), axis=0) / 1.0
x_train = x_train / 1.0

Keras 只适用于 float32 吗？

相关问题

• tensorflow 2 中的 InvalidArgumentError 是什么意思？
• InvalidArgumentError：无法计算 MatMul，因为输入 #0（从零开始）预计是浮点张量，但它是双张量 [Op:MatMul]

Answer 1

原因是preprocessing.Normalization expect float32但您的数据是uint8 ，因此出现错误。

这实际上是 Tensorflow 的问题，而不是 Keras 本身，因为这是更快的计算。

提醒：处理器中不同位置的 float 和 int 计算，每个处理器在不同数据类型上有不同的性能，例如 nvidia 的 gpus 使用float32比float16更快，而 arm cpus 使用 16 更快。

Pytorch 也需要两个变量是相同的数据类型，否则它将不起作用。

将 integer 与 python 中的浮点数相除会自动为您提供一个新的浮点数， x_train = x_train / 1.0将使x_train float32 （或float64或float16 ，具体取决于您在~/.keras/keras.json中的内容，但此处有float32 ）。