1 Answer
- Newest
- Most votes
- Most comments
0
Hi,
One reason for posting to S3 or IOT is to minimize the blocking on the process that's running the inference. If you wait for the round trip request to return results to DeepLens, the application might miss a new frame. You can certainly run a queue or state machine on the device, but I think the authors wanted to keep it simple.
answered 4 years ago
Relevant content
- asked 5 years ago
- Accepted Answerasked 3 months ago
- AWS OFFICIALUpdated 3 years ago
- AWS OFFICIALUpdated 9 months ago
- AWS OFFICIALUpdated 2 years ago
- AWS OFFICIALUpdated 2 years ago