1 Answer
- Newest
- Most votes
- Most comments
0
If you have multiple files in S3 bucket for Batch Inference, general guidelines is set the number of workers/instances = multiple of number of files in S3 to process. In addition, you can set the BatchStrategy to MultiLine in order to speed up the processing. To enable parallel processing, set the MaxConcurrentTransforms to 0 to start off, Amazon SageMaker checks the optional execution-parameters to determine the settings for your chosen algorithm.
answered 2 years ago
Relevant content
- asked 4 months ago
- asked 9 months ago
- AWS OFFICIALUpdated 2 years ago
- AWS OFFICIALUpdated 3 years ago
- AWS OFFICIALUpdated 9 months ago
@AWS-Anonymous - thanks. so if i have 2 files then set the number of instances to 2, 4, 6.... performance wise , is it better to have everything in one file , if possible , or split files up into multiple ones. Also, you mentioned "set the MaxConcurrentTransforms to 0 to start off", does this strategy work when we bring our own container, algorithm