Python Keras.backend.reforme:TypeError:转换类型为<；的对象失败；类别'；列表'&燃气轮机；到张量。将铸造元素考虑为支持类型

我正在为我的神经网络设计一个自定义层，但是我的代码出错了

我想做一个文章中描述的注意层：。和

当我在模型中添加此层时，出现了一个错误：

TypeError: Expected binary or unicode string, got Dimension(None)

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
<ipython-input-5-9d4e83945ade> in <module>()
      5 X = Conv2D(64, kernel_size=5, strides=1, name='conv1')(X)
      6 X = Activation('relu')(X)
----> 7 X = AttentionLayer()(X)
      8 X = Flatten(name='flatten2')(X)
      9 X = Dense(1000, activation='relu')(X)

/anaconda3/envs/pycharm/lib/python3.6/site-packages/keras/engine/topology.py in __call__(self, inputs, **kwargs)
    617 
    618             # Actually call the layer, collecting output(s), mask(s), and shape(s).
--> 619             output = self.call(inputs, **kwargs)
    620             output_mask = self.compute_mask(inputs, previous_mask)
    621 

~/Projects/inpainting/models/attention.py in call(self, x)
     49 
     50         # N = h * w
---> 51         flatten_g = hw_flatten(g)
     52         flatten_f = hw_flatten(f)
     53         s = K.batch_dot(flatten_g, flatten_f, axes=1)  # # [bs, N, N]

~/Projects/inpainting/models/attention.py in hw_flatten(x)
     39     def call(self, x):
     40         def hw_flatten(x):
---> 41             return K.reshape(x, shape=[x.shape[0], x.shape[1]*x.shape[2], x.shape[-1]])
     42 
     43         f = K.conv2d(x, kernel=self.kernel_f, strides=(1, 1), padding='same')  # [bs, h, w, c']

/anaconda3/envs/pycharm/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in reshape(x, shape)
   1896         A tensor.
   1897     """
-> 1898     return tf.reshape(x, shape)
   1899 
   1900 

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py in reshape(tensor, shape, name)
   6111   if _ctx is None or not _ctx._eager_context.is_eager:
   6112     _, _, _op = _op_def_lib._apply_op_helper(
-> 6113         "Reshape", tensor=tensor, shape=shape, name=name)
   6114     _result = _op.outputs[:]
   6115     _inputs_flat = _op.inputs

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
    511           except TypeError as err:
    512             if dtype is None:
--> 513               raise err
    514             else:
    515               raise TypeError(

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
    508                 dtype=dtype,
    509                 as_ref=input_arg.is_ref,
--> 510                 preferred_dtype=default_dtype)
    511           except TypeError as err:
    512             if dtype is None:

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in internal_convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, ctx)
   1102 
   1103     if ret is None:
-> 1104       ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
   1105 
   1106     if ret is NotImplemented:

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
    233                                          as_ref=False):
    234   _ = as_ref
--> 235   return constant(v, dtype=dtype, name=name)
    236 
    237 

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name, verify_shape)
    212   tensor_value.tensor.CopyFrom(
    213       tensor_util.make_tensor_proto(
--> 214           value, dtype=dtype, shape=shape, verify_shape=verify_shape))
    215   dtype_value = attr_value_pb2.AttrValue(type=tensor_value.tensor.dtype)
    216   const_tensor = g.create_op(

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape)
    519       raise TypeError("Failed to convert object of type %s to Tensor. "
    520                       "Contents: %s. Consider casting elements to a "
--> 521                       "supported type." % (type(values), values))
    522     tensor_proto.string_val.extend(str_values)
    523     return tensor_proto

TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [Dimension(None), Dimension(64), Dimension(8)]. Consider casting elements to a supported type.

TypeError:应为二进制或unicode字符串，获取维度（无）
在处理上述异常期间，发生了另一个异常：
TypeError回溯（最近一次调用上次）
在（）
5 X=Conv2D（64，内核大小=5，步幅=1，name='conv1'）（X）
6 X=激活（'relu'）（X）
---->7 X=注意层（）（X）
8 X=展平（name='flatt2'）（X）
9 X=密度（1000，活化='relu'）（X）
/anaconda3/envs/pycharm/lib/python3.6/site-packages/keras/engine/topology.py in_u_调用（self，input，**kwargs）
617
618#实际调用层，收集输出、掩码和形状。
-->619输出=自调用（输入，**kwargs）
620输出屏蔽=自计算屏蔽（输入，前一个屏蔽）
621
~/Projects/inpaint/models/attention.py在通话中（self，x）
49
50#N=h*w
--->51展平度=hw展平度（g）
52展平f=hw展平（f）
53 s=K.batch_dot（展平，展平，轴=1）35;#[bs，N，N]
~/Projects/inpaint/models/attention.py在硬件展平（x）中
39 def呼叫（自我，x）：
40 def硬件扁平化（x）：
--->41返回K.重塑（x，shape=[x.shape[0]，x.shape[1]*x.shape[2]，x.shape[-1]]
42
43 f=K.conv2d（x，kernel=self.kernel_f，步长=（1，1），padding='same'）#[bs，h，w，c']
/anaconda3/envs/pycharm/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py在整形（x，shape）中
1896张量。
1897     """
->1898返回tf。重塑（x，形状）
1899
1900
/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/ops/gen_-array_-ops.py in重塑（张量、形状、名称）
6111如果_ctx为None或not _ctx._eager_context.is eager:
6112 u，u，_op=_op_def_lib._apply_op_helper(
->6113“重塑”，张量=张量，形状=形状，名称=名称）
6114 _结果=_运算输出[：]
6115 _输入_平坦=_操作输入
/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in_apply_op_helper（self，op_type_name，name，**关键字）
511除类型错误作为错误外：
512如果数据类型为无：
-->513上升误差
514其他：
515上升类型错误(
/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in_apply_op_helper（self，op_type_name，name，**关键字）
508数据类型=数据类型，
509 as_ref=输入参数为，
-->510首选类型（默认类型）
511除类型错误作为错误外：
512如果数据类型为无：
/内部的anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/ops.py转换为tensor（值、数据类型、名称、as-ref、首选数据类型、ctx）
1102
1103如果ret为无：
->1104 ret=conversion\u func（值，dtype=dtype，name=name，as\u ref=as\u ref）
1105
1106如果未实施ret：
/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in_constant_tensor_conversion_函数（v，dtype，name，as_ref）
233 as_ref=False）：
234=作为参考
-->235返回常量（v，dtype=dtype，name=name）
236
237
/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in constant（值、数据类型、形状、名称、验证形状）
212 tensor_value.tensor.CopyFrom(
213张量使用。生成张量原型(
-->214值，dtype=dtype，shape=shape，verify_shape=verify_shape））
215 dtype\u value=attr\u value\u pb2.AttrValue（type=tensor\u value.tensor.dtype）
216常数张量=g.create\u op(
/make_tensor_proto中的anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py（值、数据类型、形状、验证形状）
519 raise TypeError（“未能将%s类型的对象转换为Tensor。”
520“内容：%s考虑铸造元素为”
-->521“支持的类型”。%（类型（值），值））
522张量原始字符串值扩展（str值）
523返回张量
TypeError：将类型对象转换为张量失败。内容：[维度（无），维度（64），维度（8）]。

---

我试图在hw_flatten函数中设置

x_shape=x.shape.as_list（）

，但它不起作用，我不知道如何调试此错误。

您正在访问tensor的

.shape

属性，该属性为您提供尺寸对象，而不是实际的形状值。您有两个选项：

如果您知道形状，并且它在图层创建时是固定的，则可以使用

K.int\u shape（x）[0]

将值作为整数给出。但是，如果形状在创建时未知，例如，如果批次大小未知，它将返回

None

如果形状将在运行时确定，则可以使用

K.shape（x）[0]

，它将返回一个符号张量，在运行时保存形状值

---

您正在访问tensor的

.shape

属性，该属性为您提供标注对象，而不是实际的形状值。您有两个选项：

如果您知道形状，并且它在图层创建时是固定的，则可以使用

K.int\u shape（x）[0]

将值作为整数给出。但是，如果形状在创建时未知，例如，如果批次大小未知，它将返回

None

如果形状是

TypeError: Expected binary or unicode string, got Dimension(None)

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
<ipython-input-5-9d4e83945ade> in <module>()
      5 X = Conv2D(64, kernel_size=5, strides=1, name='conv1')(X)
      6 X = Activation('relu')(X)
----> 7 X = AttentionLayer()(X)
      8 X = Flatten(name='flatten2')(X)
      9 X = Dense(1000, activation='relu')(X)

/anaconda3/envs/pycharm/lib/python3.6/site-packages/keras/engine/topology.py in __call__(self, inputs, **kwargs)
    617 
    618             # Actually call the layer, collecting output(s), mask(s), and shape(s).
--> 619             output = self.call(inputs, **kwargs)
    620             output_mask = self.compute_mask(inputs, previous_mask)
    621 

~/Projects/inpainting/models/attention.py in call(self, x)
     49 
     50         # N = h * w
---> 51         flatten_g = hw_flatten(g)
     52         flatten_f = hw_flatten(f)
     53         s = K.batch_dot(flatten_g, flatten_f, axes=1)  # # [bs, N, N]

~/Projects/inpainting/models/attention.py in hw_flatten(x)
     39     def call(self, x):
     40         def hw_flatten(x):
---> 41             return K.reshape(x, shape=[x.shape[0], x.shape[1]*x.shape[2], x.shape[-1]])
     42 
     43         f = K.conv2d(x, kernel=self.kernel_f, strides=(1, 1), padding='same')  # [bs, h, w, c']

/anaconda3/envs/pycharm/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in reshape(x, shape)
   1896         A tensor.
   1897     """
-> 1898     return tf.reshape(x, shape)
   1899 
   1900 

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py in reshape(tensor, shape, name)
   6111   if _ctx is None or not _ctx._eager_context.is_eager:
   6112     _, _, _op = _op_def_lib._apply_op_helper(
-> 6113         "Reshape", tensor=tensor, shape=shape, name=name)
   6114     _result = _op.outputs[:]
   6115     _inputs_flat = _op.inputs

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
    511           except TypeError as err:
    512             if dtype is None:
--> 513               raise err
    514             else:
    515               raise TypeError(

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
    508                 dtype=dtype,
    509                 as_ref=input_arg.is_ref,
--> 510                 preferred_dtype=default_dtype)
    511           except TypeError as err:
    512             if dtype is None:

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in internal_convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, ctx)
   1102 
   1103     if ret is None:
-> 1104       ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
   1105 
   1106     if ret is NotImplemented:

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
    233                                          as_ref=False):
    234   _ = as_ref
--> 235   return constant(v, dtype=dtype, name=name)
    236 
    237 

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name, verify_shape)
    212   tensor_value.tensor.CopyFrom(
    213       tensor_util.make_tensor_proto(
--> 214           value, dtype=dtype, shape=shape, verify_shape=verify_shape))
    215   dtype_value = attr_value_pb2.AttrValue(type=tensor_value.tensor.dtype)
    216   const_tensor = g.create_op(

/anaconda3/envs/pycharm/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape)
    519       raise TypeError("Failed to convert object of type %s to Tensor. "
    520                       "Contents: %s. Consider casting elements to a "
--> 521                       "supported type." % (type(values), values))
    522     tensor_proto.string_val.extend(str_values)
    523     return tensor_proto

TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [Dimension(None), Dimension(64), Dimension(8)]. Consider casting elements to a supported type.