python - Keras.backend.reshape : TypeError: Failed to convert object of type to Tensor. 考虑将元素转换为支持的类型

Question

我正在为我的神经网络设计一个自定义层，但我的代码出现错误。

我想做一个注意力层，如论文中所述:SAGAN .和 original tf code

class AttentionLayer(Layer):
def __init__(self, **kwargs):
    super(AttentionLayer, self).__init__(**kwargs)

def build(self, input_shape):
    input_dim = input_shape[-1]
    filters_f_g = input_dim // 8
    filters_h = input_dim
    kernel_shape_f_g = (1, 1) + (input_dim, filters_f_g)
    kernel_shape_h = (1, 1) + (input_dim, filters_h)
    # Create a trainable weight variable for this layer:
    self.gamma = self.add_weight(name='gamma', shape=[1], initializer='zeros', trainable=True)
    self.kernel_f = self.add_weight(shape=kernel_shape_f_g,
                                    initializer='glorot_uniform',
                                    name='kernel')
    self.kernel_g = self.add_weight(shape=kernel_shape_f_g,
                                    initializer='glorot_uniform',
                                    name='kernel')
    self.kernel_h = self.add_weight(shape=kernel_shape_h,
                                    initializer='glorot_uniform',
                                    name='kernel')
    self.bias_f = self.add_weight(shape=(filters_f_g,),
                                  initializer='zeros',
                                  name='bias')
    self.bias_g = self.add_weight(shape=(filters_f_g,),
                                  initializer='zeros',
                                  name='bias')
    self.bias_h = self.add_weight(shape=(filters_h,),
                                  initializer='zeros',
                                  name='bias')
    super(AttentionLayer, self).build(input_shape)

def call(self, x):
    def hw_flatten(x):
        return K.reshape(x, shape=[x.shape[0], x.shape[1]*x.shape[2], x.shape[-1]])

    f = K.conv2d(x, kernel=self.kernel_f, strides=(1, 1), padding='same')  # [bs, h, w, c']
    f = K.bias_add(f, self.bias_f)
    g = K.conv2d(x, kernel=self.kernel_g, strides=(1, 1), padding='same')  # [bs, h, w, c']
    g = K.bias_add(g, self.bias_g)
    h = K.conv2d(x, kernel=self.kernel_h, strides=(1, 1), padding='same')  # [bs, h, w, c]
    h = K.bias_add(h, self.bias_h)

    # N = h * w
    flatten_g = hw_flatten(g)
    flatten_f = hw_flatten(f)
    s = K.batch_dot(flatten_g, flatten_f, axes=1)  # # [bs, N, N]

    beta = K.softmax(s, axis=-1)  # attention map

    o = K.batch_dot(beta, hw_flatten(h))  # [bs, N, C]

    o = K.reshape(o, shape=x.shape)  # [bs, h, w, C]
    x = self.gamma * o + x

    return x

当我在模型中添加这个层时，我得到一个错误:

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.

我尝试在 hw_flatten 函数中制作 x_shape = x.shape.as_list() ，但它不起作用，我不知道如何调试此错误。

Answer 1

您正在访问张量的 .shape 属性，该属性为您提供 Dimension 对象，而不是实际的形状值。你有两个选择:

1. 如果您知道形状并且它在图层创建时已固定，您可以使用 K.int_shape(x)[0] 将值作为整数给出。但是，如果在创建时形状未知，它将返回 None；例如，如果 batch_size 未知。
2. 如果形状将在运行时确定，那么您可以使用 K.shape(x)[0] 它将返回一个符号张量，该张量将在运行时保存形状值。