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.
Response for PredictRequest on successful run.
Response for PredictRequest on successful run.
Output tensors.
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.
Model Specification.
Input tensors. Names of input tensor are alias names. The mapping from aliases to real input tensor names is stored in the SavedModel export as a prediction SignatureDef under the 'inputs' field.
Output filter. Names specified are alias names. The mapping from aliases to real output tensor names is stored in the SavedModel export as a prediction SignatureDef under the 'outputs' field. 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.