batchStrategy
Specifies the number of records to include in a mini-batch for an HTTP inference request. A record** is a single unit of input data that inference can be made on. For example, a single line in a CSV file is a record.
To enable the batch strategy, you must set the SplitType
property to Line
, RecordIO
, or TFRecord
.
To use only one record when making an HTTP invocation request to a container, set BatchStrategy
to SingleRecord
and SplitType
to Line
.
To fit as many records in a mini-batch as can fit within the MaxPayloadInMB
limit, set BatchStrategy
to MultiRecord
and SplitType
to Line
.