package tensorflow.serving

Get desktop application:
View/edit binary Protocol Buffers messages

PredictionService provides access to machine-learned models loaded by model_servers.

• rpc Predict (PredictRequest, PredictResponse)

  prediction_service.proto:12

  Predict -- provides access to loaded TensorFlow model.

  message PredictRequest

  predict.proto:12

  PredictRequest specifies which TensorFlow model to run, as well as how inputs are mapped to tensors and how outputs are filtered before returning to user.

  • optional ModelSpec model_spec = 1

    Model Specification.

  • map<string, TensorProto> inputs = 2

    Input tensors. Names of input tensor are alias names. The mapping from aliases to real input tensor names is expected to be stored as named generic signature under the key "inputs" in the model export. Each alias listed in a generic signature named "inputs" should be provided exactly once in order to run the prediction.

  • repeated string output_filter = 3

    Output filter. Names specified are alias names. The mapping from aliases to real output tensor names is expected to be stored as named generic signature under the key "outputs" in the model export. Only tensors specified here will be run/fetched and returned, with the exception that when none is specified, all tensors specified in the named signature will be run/fetched and returned.

  message PredictResponse

  predict.proto:35

  Response for PredictRequest on successful run.

  • map<string, TensorProto> outputs = 1

    Output tensors.

Metadata for an inference request such as the model name and version.

Used in: PredictRequest

• string name = 1

  Required servable name.

• optional google.protobuf.Int64Value version = 2

  Optional version. If unspecified, will use the latest (numerical) version. Typically not needed unless coordinating across multiple models that were co-trained and/or have inter-dependencies on the versions used at inference time.

• string signature_name = 3

  A named signature to evaluate. If unspecified, the default signature will be used. Note that only MultiInference will initially support this.