python - Python Keras TypeError('预期的二进制或 unicode 字符串，得到 %r' % TypeError: 预期的二进制或 unicode 字符串，得到 1

Question

通过运行包含更快 rcnn 的 keras 实现的 test.py 脚本，我收到了这个错误：

  raise TypeError('Expected binary or unicode string, got %r' %
  TypeError: Expected binary or unicode string, got 1

丰富：

  During handling of the above exception, another exception occurred:

  Traceback (most recent call last):
  File test_frcnn.py", line 125, in <module>
  shared_layers = nn.nn_base(img_input, trainable=False)
  File resnet.py", line 183, in nn_base
  x = FixedBatchNormalization(axis=bn_axis, name='bn_conv1')(x)

  raise TypeError("Failed to convert object of type %s to Tensor. "
  TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [1, None, 1, 1]. 
  Consider casting elements to a supported type.

这是一个非常奇怪的行为，因为它在我的笔记本电脑上返回此错误，而它在 google colab 上完美运行。它是什么？编译器是否有可能返回此错误，因为我已经使用 colab GPU 训练了模型，而现在我正在使用 CPU 在笔记本电脑上编译测试？

完整的追溯：

Traceback (most recent call last):
  File test.py", line 125, in <module>
    shared_layers = nn.nn_base(img_input, trainable=False)
  resnet.py", line 183, in nn_base
    x = FixedBatchNormalization(axis=bn_axis, name='bn_conv1')(x)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/keras/backend/tensorflow_backend.py", line 75, in symbolic_fn_wrapper
    return func(*args, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/keras/engine/base_layer.py", line 489, in __call__
    output = self.call(inputs, **kwargs)
  File "/Users/federicolisi/PycharmProjects/neural_networks_GIT/MakeUp_v2/keras-frcnn/keras_frcnn/FixedBatchNormalization.py", line 66, in call
    broadcast_running_mean = K.reshape(self.running_mean, broadcast_shape)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/keras/backend/tensorflow_backend.py", line 2440, in reshape
    return tf.reshape(x, shape)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/tensorflow/python/ops/array_ops.py", line 193, in reshape
    result = gen_array_ops.reshape(tensor, shape, name)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/tensorflow/python/ops/gen_array_ops.py", line 8086, in reshape
    _, _, _op, _outputs = _op_def_library._apply_op_helper(
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/tensorflow/python/framework/op_def_library.py", line 473, in _apply_op_helper
    raise err
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/tensorflow/python/framework/op_def_library.py", line 465, in _apply_op_helper
    values = ops.convert_to_tensor(
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/tensorflow/python/framework/ops.py", line 1341, in convert_to_tensor
    ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 321, in _constant_tensor_conversion_function
    return constant(v, dtype=dtype, name=name)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 261, in constant
    return _constant_impl(value, dtype, shape, name, verify_shape=False,
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 298, in _constant_impl
    tensor_util.make_tensor_proto(
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/tensorflow/python/framework/tensor_util.py", line 545, in make_tensor_proto
    raise TypeError("Failed to convert object of type %s to Tensor. "
TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [1, None, 1, 1]. Consider casting elements to a supported type.

标签： pythonkerastensorflow2.0