VideoContentSearchDolphinScoringConfig

Description

Attributes List

This module has the following attributes (case-insensitive ascending order):

Attributes

1. descriptivenessOutputKey (type: String.t, default: nil)
   - The output put keys for Dolphin PredictResponse
2. ensembleModelNames (type: list(String.t), default: nil)
   - If the dolphin model is an ensemble model (e.g. Video QnA model which consists of 4 teacher models), stores each individual model name.
3. inferenceBatchSize (type: integer(), default: nil)
   - The inference batch size to use for inference methods that handle batching.
4. inferenceMethod (type: String.t, default: nil)
   - The method to use for inference. This must be set or inference will fail.
5. maxRpcRetries (type: integer(), default: nil)
   - Holds value of flag --max_rpc_retries.
6. modelName (type: String.t, default: nil)
   - Model name used for ModelSpec in PredictRequest used in the PredictionService API.
7. modelPath (type: String.t, default: nil)
   - Only used when using the bulk_inference API. See go/dolphin-models to learn about the different dolphin models.
8. outputKey (type: String.t, default: nil)
   - TODO(alexiaxu) To deprecate this field in the future Output key for Dolphin PredictResponse.
9. rpcDeadlineSeconds (type: float(), default: nil)
   - Holds value of flag --rpc_deadline (converted to seconds).
10. serviceBns (type: String.t, default: nil)
    - Tensorflow inference BNS address when using PredictionService API.
11. usefulnessOutputKey (type: String.t, default: nil)
    -

Type

Function

Data sourced from HexDocs : GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchDolphinScoringConfig

• ‹ VideoContentSearchDolphinFeatures
• VideoContentSearchEntityAnnotations ›

Possibly related Links