Scott Uhlrich

Or we just do default if 2 scales fails On Jun 6, 2023, at 10:27 PM, Antoine Falisse ***@***.***> wrote:  How about we try 2 scales if default fails?...

Argh. Perhaps thru reprocess?

this should be on the api side: https://github.com/stanfordnmbl/opencap-core/blob/943b0c01cf96bac3ae23898e7a246aaa8adca314/utilsServer.py#L148

2. The problem lies with our base capacity. We want to turn off the EC2 instances once the number of jobs falls below some threshold that we think is managable...

Sounds good. Sounds like we should create an API endpoint that returns number_of_jobs. (unless there's an easy way to get it from cloudwatch, but an http request sounds easy to...

how would we query cloudwatch? Would this be another batch script? I guess it is probably better to be looking at the same value that the ASG rule is looking...

No. Let's remove the docker part. Scott Uhlrich, PhD Director of Research | Human Performance Lab Bioengineering Department Stanford University website ________________________________ From: Antoine Falisse ***@***.***> Sent: Thursday, February 8,...

we could do the "find the biggest box across video and track it" approach that we use downstream. Not sure how easy it is to modify that.

nice. let's first verify that pose est of 1 box makes things faster/ less memory before all the work to do it right.

I assume it is regularized by default cuz the initial guess is prob 0? So for normal camera-facing motions, will we consistently get 0?