error when serving seq_tagger model

[alucardpj]

I trained a seq_tagger model and serve it using tensorflow serving, but when I test the serving model, I got the error message:

grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.INVALID_ARGUMENT, details="Placeholder_3:0 is both fed and fetched.")

the model detailed info is below:

The given SavedModel SignatureDef contains the following input(s):
inputs['chars'] tensor_info:
dtype: DT_STRING
shape: (-1, -1, -1)
name: Placeholder_2:0
inputs['length'] tensor_info:
dtype: DT_INT32
shape: (-1)
name: Placeholder_3:0
inputs['tokens'] tensor_info:
dtype: DT_STRING
shape: (-1, -1)
name: Placeholder:0
The given SavedModel SignatureDef contains the following output(s):
outputs['length'] tensor_info:
dtype: DT_INT32
shape: (-1)
name: Placeholder_3:0
outputs['tags'] tensor_info:
dtype: DT_STRING
shape: (-1, -1)
name: seqtagger/index_to_string_Lookup:0
Method name is: tensorflow/serving/predict

it shows that the inputs['length'] and the output['length'] are the same placeholder, so it raise error.