我正在尝试将天赋嵌入作为新层添加到 keras 模型中，但出现此错误：

TypeError: Inputs to a layer should be tensors. Got: PooledflairEmbeddings(
  (context_embeddings): flairEmbeddings(
    (lm): LanguageModel(
      (drop): Dropout(p=0.05,inplace=False)
      (encoder): Embedding(300,100)
      (rnn): LSTM(100,2048)
      (decoder): Linear(in_features=2048,out_features=300,bias=True)
    )
  )
)

这是我的代码：

from flair.embeddings import PooledflairEmbeddings


flair_embedding_forward = PooledflairEmbeddings('news-forward')
model = flair_embedding_forward
#model = StackedEmbeddings(embeddings=[flair_forward_embedding,flair_backward_embedding,bert_embedding])(model)


model = Bidirectional(LSTM(units=word_embedding_size,return_sequences=True,dropout=0.5,recurrent_dropout=0.5 
                           ))(model)
model = LSTM(units=word_embedding_size * 2,recurrent_dropout=0.5,kernel_initializer=k.initializers.he_normal())(model)

另外，如果我尝试添加输入：

input = Input(shape=(120,))
word_embedding_size = 150

# Embedding Layer
#model = Embedding(input_dim=input_dim,output_dim=output_dim,input_length=140)(input)
from flair.embeddings import PooledflairEmbeddings

# init embedding
flair_embedding_forward = PooledflairEmbeddings('news-forward')(input)

我收到此错误：

NotImplementedError                       Traceback (most recent call last)
<ipython-input-23-5af77228f209> in <module>()
     16 
     17 # init embedding
---> 18 flair_embedding_forward = PooledflairEmbeddings('news-forward')(input)
     19 model = flair_embedding_forward
     20 #model = StackedEmbeddings(embeddings=[flair_forward_embedding,bert_embedding])(model)

1 frames
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _forward_unimplemented(self,*input)
    173         registered hooks while the latter silently ignores them.
    174     """
--> 175     raise NotImplementedError
    176 
    177 

NotImplementedError: 

关于如何添加词嵌入而不会出错的任何帮助？