Tensorflow/Numpy：对象__array__方法不产生数组

Question

我对机器学习比较陌生，正在尝试规范化一些数据。这是一个代码 sn-p。

import numpy as np
import tensorflow as tf
from tensorflow.keras.layers.experimental import preprocessing

data = np.array([[0.1, 0.2, 0.3], [0.8, 0.9, 1.0], [1.5, 1.6, 1.7],])
layer = preprocessing.Normalization()
layer.adapt(data)
normalized_data = layer(data)

但是，当我运行代码时，Python 告诉我对象数组方法没有生成数组。

ValueError                                Traceback (most recent call last)
<ipython-input-2-97aa44cf6880> in <module>()
      5 data = np.array([[0.1, 0.2, 0.3], [0.8, 0.9, 1.0], [1.5, 1.6, 1.7],])
      6 layer = preprocessing.Normalization()
----> 7 layer.adapt(data)
      8 normalized_data = layer(data)

~\.conda\envs\py35\lib\site-packages\tensorflow\python\keras\engine\base_preprocessing_layer.py in adapt(self, data, reset_state)
    214 
    215     updates = self._combiner.extract(accumulator)
--> 216     self._set_state_variables(updates)
    217 
    218   def _set_state_variables(self, updates):

~\.conda\envs\py35\lib\site-packages\tensorflow\python\keras\engine\base_preprocessing_layer.py in _set_state_variables(self, updates)
    235     with ops.init_scope():
    236       for var_name, value in updates.items():
--> 237         self.state_variables[var_name].assign(value)
    238 
    239 

~\.conda\envs\py35\lib\site-packages\tensorflow\python\ops\resource_variable_ops.py in assign(self, value, use_locking, name, read_value)
    855     # initialize the variable.
    856     with _handle_graph(self.handle):
--> 857       value_tensor = ops.convert_to_tensor(value, dtype=self.dtype)
    858       self._shape.assert_is_compatible_with(value_tensor.shape)
    859       assign_op = gen_resource_variable_ops.assign_variable_op(

~\.conda\envs\py35\lib\site-packages\tensorflow\python\framework\ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
   1497 
   1498     if ret is None:
-> 1499       ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
   1500 
   1501     if ret is NotImplemented:

~\.conda\envs\py35\lib\site-packages\tensorflow\python\framework\tensor_conversion_registry.py in _default_conversion_function(***failed resolving arguments***)
     50 def _default_conversion_function(value, dtype, name, as_ref):
     51   del as_ref  # Unused.
---> 52   return constant_op.constant(value, dtype, name=name)
     53 
     54 

~\.conda\envs\py35\lib\site-packages\tensorflow\python\framework\constant_op.py in constant(value, dtype, shape, name)
    262   """
    263   return _constant_impl(value, dtype, shape, name, verify_shape=False,
--> 264                         allow_broadcast=True)
    265 
    266 

~\.conda\envs\py35\lib\site-packages\tensorflow\python\framework\constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
    273       with trace.Trace("tf.constant"):
    274         return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
--> 275     return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
    276 
    277   g = ops.get_default_graph()

~\.conda\envs\py35\lib\site-packages\tensorflow\python\framework\constant_op.py in _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
    298 def _constant_eager_impl(ctx, value, dtype, shape, verify_shape):
    299   """Implementation of eager constant."""
--> 300   t = convert_to_eager_tensor(value, ctx, dtype)
    301   if shape is None:
    302     return t

~\.conda\envs\py35\lib\site-packages\tensorflow\python\framework\constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
     96       dtype = dtypes.as_dtype(dtype).as_datatype_enum
     97   ctx.ensure_initialized()
---> 98   return ops.EagerTensor(value, ctx.device_name, dtype)
     99 
    100 

ValueError: object __array__ method not producing an array

我做了一些研究，但找不到任何问题的答案。 我究竟做错了什么？我在 Win10 上运行 Tensorflow 版本 2.3.0、Numpy 1.14.2、Python 3.5。

谢谢你们的帮助，伙计们！

Answer 1

我能够在 Colab 上使用 numpy 1.18.5 和 TF 2.4.1 和 1.19.5 在 TF 2.3 中执行您的代码。

import numpy as np
import tensorflow as tf
print(tf.__version__)
print(np.__version__)

from tensorflow.keras.layers.experimental import preprocessing

data = np.array([[0.1, 0.2, 0.3], [0.8, 0.9, 1.0], [1.5, 1.6, 1.7],])
layer = preprocessing.Normalization()
layer.adapt(data)
normalized_data = layer(data)
print(normalized_data)

输出：

2.3.0
1.18.5
tf.Tensor(
[[-1.2247449 -1.2247449 -1.2247449]
 [ 0.         0.         0.       ]
 [ 1.2247449  1.224745   1.224745 ]], shape=(3, 3), dtype=float32)