Re:AMD Alveo V70 AI inference accelerator card
by inetsee on Tuesday January 10, 2023 @10:51AM
(#34326661)
I have no problem imagining a security camera application needing to monitor quite a few video channels.
Re:AMD Alveo V70 AI inference accelerator card
by h2odragon on Tuesday January 10, 2023 @11:25AM
(#34327260)
Certainly. I'm suspecting that doing much of anything with all 96 channels would really need more RAM, for most users.
Re:AMD Alveo V70 AI inference accelerator card
by scottlamb on Tuesday January 10, 2023 @12:34PM
(#34328400)
On the inference accelerator? IIUC, the RAM is just to hold the model and whatever state it needs during a particular inference operation. I'm not an expert on ML but AFAIK 16 GiB is plenty. I suppose it'd also need to hold onto reference frames for the video decoding, but at 1080p with e.g. YUV420 (12 bits per pixel), you can hold a lot of those in 16 GiB. edit: e.g., 4 references for each of the 96 streams would take ~1 GiB.
Even on the host, 16 GiB is fine for say an NVR. They don't do need to keep a lot of state in RAM (or for that matter to do a lot of on-CPU computation either).
Re:AMD Alveo V70 AI inference accelerator card
by andy_ppp on Tuesday January 10, 2023 @11:00AM
(#34326853)
/camera/state/g
Re:AMD Alveo V70 AI inference accelerator card
by phkahler on Tuesday January 10, 2023 @11:54AM
(#34327726)
>> I have no problem imagining a security camera application needing to monitor quite a few video channels.
As a joke I sometimes tell people the automatic flushing toilets in public bathrooms work by having a little camera monitored by someone in a 3rd world country who remotely flushes as needed, while monitoring a whole lot of video feeds. They usually don't buy it, but will often acknowledge that our world is uncomfortably close to having stuff like become reality.
Re:AMD Alveo V70 AI inference accelerator card
by hhh on Tuesday January 10, 2023 @01:42PM
(#34329450)
I have models in production that currently monitor ~400 cameras with an addition of 2-3 cameras/month. If it were cheap enough, it would be useful for our use case (Quality Control). We generally pull from cameras roughly 6400 pixels per region of interest, of which one instance may have 4-30 RoIs across N cameras.
Re:AMD Alveo V70 AI inference accelerator card
by 71a54xd on Tuesday January 10, 2023 @02:00PM
(#34329725)
Curious where I could learn more about models like this / potentially see some open code outlining tooling / infra required as well?
Re:AMD Alveo V70 AI inference accelerator card
by hhh on Tuesday January 10, 2023 @02:51PM
(#34330510)
Not sure about open information about the models, but from tooling/infra we are running k8s w/ in-house API for image acquisition. Features are defined as x,y coordinates denoting center of a feature, with a pixel count denoting size of rectangle in each direction from center.
16gb RAM / 96 video channels ... I haven't done any of that work but it feels like they expect that "96" not to be fully used in practice.