LSTM 模型没有被实例化

Question

我正在尝试为 NER 任务创建一个基线模型，使用双向 LSTM 和 Keras

提供的函数 API

我用的embedding层是100维的特征向量

层的输入是长度为

的填充序列

MAX_LEN = 575

（注意：输入和输出的维度相同）

我想要在每个时间步都有一个输出，因此我设置了

return_sequences = True

输出只是通过soft-max层

的激活

但是在编译模型时我不断收到此警告

UserWarning: Model inputs must come from `keras.layers.Input`
(thus holding past layer metadata), they cannot be the output of a 
previous non-Input layer. Here, a tensor specified as input to your model was
not an Input tensor, it was generated by layer embedding_3.
Note that input tensors are instantiated via `tensor = keras.layers.Input(shape)`.
The tensor that caused the issue was: embedding_3_40/embedding_lookup/Identity:0 str(x.name))

伴随着

AssertionError:

回溯：

---> 37 model = Model(inputs = nn_input, outputs = nn_output)
---> 91             return func(*args, **kwargs)
---> 93             self._init_graph_network(*args, **kwargs)
    222             # It's supposed to be an input layer, so only one node
    223             # and one tensor output.
--> 224             assert node_index == 0

我尝试调试代码以检查尺寸，但它们似乎与代码中注释突出显示的一致

nn_input = Input(shape = (MAX_LEN,) , dtype = 'int32')

print(nn_input.shape)   #(?, 575)

nn_input = embedding_layer(nn_input)

print(nn_input.shape)   #(?, 575, 100)

nn_out, forward_h, forward_c, backward_h, backward_c = Bidirectional(LSTM(MAX_LEN, return_sequences = True, return_state = True))(nn_input)

print(forward_h.shape)  #(?, 575)
print(forward_c.shape)  #(?, 575)
print(backward_h.shape) #(?, 575)
print(backward_c.shape) #(?, 575)

print(nn_out.shape)     #(?, ?, 1150)

state_h = Concatenate()([forward_h, backward_h])
state_c = Concatenate()([forward_c, backward_c])

print(state_h.shape)    #(?, 1150)
print(state_c.shape)    #(?, 1150)

densor = Dense(100, activation='softmax')
nn_output = densor(nn_out)

print(nn_output.shape)  #(?, 575, 100)

model = Model(inputs = nn_input, outputs = nn_output)

这对某些人来说似乎微不足道，但我担心我对 LSTM 或至少 Keras 的理解存在缺陷

如有必要，我会在编辑中提供更多详细信息

非常感谢任何帮助！

Answer 1

如错误所示，您必须将层 keras.layers.Input 的输出张量传递给模型 API。在这种情况下，张量 nn_input 是 embedding_layer 的输出。将用于分配 embedding_layer 输出的变量名从 nn_input 更改为其他名称。

nn_input = Input(shape = (MAX_LEN,) , dtype = 'int32')
# the line below is the cause of the error. Change the output variable name to like nn_embed. 
nn_input = embedding_layer(nn_input)

LSTM 模型没有被实例化

LSTM Model not getting instantiated

bidirectional

lstm

keras