我正在以 bilstm-attention-conv1d 方式构建模型（我想使用具有不同内核大小的多个 conv1d）我面临着注意力层和 conv1d 层之间的层不兼容问题。我尝试过 Reshape 功能，但它不起作用，以下是我的代码：
我的模型如下
sequence_input = Input(shape=(maxlen,), dtype="int32")
embedded_sequences = Embedding(50000, output_dim=output_dim)(sequence_input)
lstm = Bidirectional(LSTM(RNN_CELL_SIZE, return_sequences = True), name="bi_lstm_0")(embedded_sequences)
# Getting our LSTM outputs
(lstm, forward_h, forward_c, backward_h, backward_c) = Bidirectional(LSTM(RNN_CELL_SIZE, return_sequences=True, return_state=True),
name="bi_lstm_1")(lstm)
state_h = Concatenate()([forward_h, backward_h])
state_c = Concatenate()([forward_c, backward_c])
context_vector, attention_weights = Attention(10)(lstm, state_h)
x = Reshape((maxlen, output_dim, 1))(context_vector)
kernel_sizes = [1,2,3,4,5]
convs = []
for kernel_size in range(len(kernel_sizes)):
conv = Conv1D(128, kernel_size, activation='relu')(x)
convs.append(conv)
avg_pool = GlobalAveragePooling1D()(convs)
max_pool = GlobalMaxPooling1D()(convs)
conc = concatenate([avg_pool, max_pool])
output = Dense(50, activation="sigmoid")(conc)
model = keras.Model(inputs=sequence_input, outputs=output)
print(model.summary())
我的代码给了我以下错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-114-8e5c0c75e84a> in <module>()
13 context_vector, attention_weights = Attention(10)(lstm, state_h)
14
---> 15 x = Reshape((maxlen, output_dim, 1))(context_vector)
16
17
6 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
950 if _in_functional_construction_mode(self, inputs, args, kwargs, input_list):
951 return self._functional_construction_call(inputs, args, kwargs,
--> 952 input_list)
953
954 # Maintains info about the `Layer.call` stack.
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py in _functional_construction_call(self, inputs, args, kwargs, input_list)
1089 # Check input assumptions set after layer building, e.g. input shape.
1090 outputs = self._keras_tensor_symbolic_call(
-> 1091 inputs, input_masks, args, kwargs)
1092
1093 if outputs is None:
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py in _keras_tensor_symbolic_call(self, inputs, input_masks, args, kwargs)
820 return nest.map_structure(keras_tensor.KerasTensor, output_signature)
821 else:
--> 822 return self._infer_output_signature(inputs, args, kwargs, input_masks)
823
824 def _infer_output_signature(self, inputs, args, kwargs, input_masks):
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py in _infer_output_signature(self, inputs, args, kwargs, input_masks)
861 # TODO(kaftan): do we maybe_build here, or have we already done it?
862 self._maybe_build(inputs)
--> 863 outputs = call_fn(inputs, *args, **kwargs)
864
865 self._handle_activity_regularization(inputs, outputs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/core.py in call(self, inputs)
555 # Set the static shape for the result since it might lost during array_ops
556 # reshape, eg, some `None` dim in the result could be inferred.
--> 557 result.set_shape(self.compute_output_shape(inputs.shape))
558 return result
559
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/core.py in compute_output_shape(self, input_shape)
546 output_shape = [input_shape[0]]
547 output_shape += self._fix_unknown_dimension(input_shape[1:],
--> 548 self.target_shape)
549 return tensor_shape.TensorShape(output_shape)
550
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/core.py in _fix_unknown_dimension(self, input_shape, output_shape)
534 output_shape[unknown] = original // known
535 elif original != known:
--> 536 raise ValueError(msg)
537 return output_shape
538
ValueError: total size of new array must be unchanged, input_shape = [256], output_shape = [2500, 100, 1]
请帮助我