kyagu
Reputation: 183
how to structure input/formats for batch inference in sagemaker?
example provided in the aws documentation , https://docs.aws.amazon.com/sagemaker/latest/dg/batch-transform.html, states that the input csv can be structured like a sample below. I noticed for batch jobs in sagemaker, it can accept json as well. how to structure the json, does each record need to in a single line as shown in a csv example or can it be multiline?
Record1-Attribute1, Record1-Attribute2, Record1-Attribute3, ..., Record1-AttributeM
...
Upvotes: 0
Views: 1082
Answers (1)
Marc Karp
Reputation: 1314
It is recommended to make use of JSON Lines (i.e. each JSON to be on a single line). You can then set BatchStrategy to MultiRecord and SplitType to Line.
Batch Transform can then fit as many records in a mini-batch within the MaxPayloadInMB limit.
Kindly see the CreateTransformJob API for more information.
Upvotes: 1
Related Questions
- Sagemaker batch transform job - Input data location
- how to run a batch transform job in sagemaker pipeline via custom inference code?
- Preprocessing data before inference in Batch Transform SageMaker
- How to get batch predictions with jsonl data in sagemaker?
- Input data for Amazon Sagemaker Python SDK
- How to match input/output with sagemaker batch transform?
- Shared input in Sagemaker inference pipeline models
- How to custom code an inference pipeline in AWS sagemaker?
- Using the same preprocessing code for both training and inference in sagemaker
- how can I preprocess input data before making predictions in sagemaker?