Tensor2Tensor（T2T）转换Tensorflow服务输入

Question

下面是我的翻译模型的signature_def。如何从EagerTensor创建serialized_example？

  signature_def {
    key: "serving_default"
    value {
      inputs {
        key: "input"
        value {
          name: "serialized_example:0"
          dtype: DT_STRING
          tensor_shape {
            dim {
              size: -1
            }
          }
        }
      }
      outputs {
        key: "batch_prediction_key"
        value {
          name: "Identity:0"
          dtype: DT_INT32
          tensor_shape {
            dim {
              size: -1
            }
            dim {
              size: 1
            }
          }
        }
      }
      outputs {
        key: "outputs"
        value {
          name: "transformer/while/Exit_3:0"
          dtype: DT_INT64
          tensor_shape {
            dim {
              size: -1
            }
            dim {
              size: -1
            }
          }
        }
      }
      outputs {
        key: "scores"
        value {
          name: "transformer/while/Exit_36:0"
          dtype: DT_FLOAT
          tensor_shape {
            dim {
              size: -1
            }
          }
        }
      }
      method_name: "tensorflow/serving/predict"
    }
  }