Can I ingest embeddings instead of frames for training, labelling and predictions for the AWS Rekognition custom label?

Question

I am thinking of storing image embedding in a feature store and use the AWS Rekognition custom label and I am weighing whether it is better to store frames/embeddings/image hashes. But before that I would like to know if it is possible to use embeddings/image hashes for training/prediction/labelling rather than images. Thank you!

Answer

Hello,

Custom Label only support image input. Please refer (https://aws.amazon.com/rekognition/custom-labels-features/)[ https://aws.amazon.com/rekognition/custom-labels-features/] for additional details.

You can also explore sagemaker training [options](https://docs.aws.amazon.com/sagemaker/latest/dg/train-model.html) for the use-case.

Thanks

Can I ingest embeddings instead of frames for training, labelling and predictions for the AWS Rekognition custom label?

Relevant content