@NateMeyer commented on GitHub (Feb 13, 2024):
TensorRT 8.5.3 claims to support compute 5.0, but I don't have one of those cards to test with. Do we know of anyone with a Maxwell GPU that is…
@hamishfagg commented on GitHub (Feb 9, 2024):
I seem to have the same issue as here: #8329 - I get keyerrors if I use USE_FP16=false which apparently I need to use for my card.
There is one…
@BunpGhost commented on GitHub (Feb 12, 2024):
I to am having the same issue.
I have a quadro k1200
Also using USE_FP16=false .
@BunpGhost commented on GitHub (Feb 12, 2024):
I to am having the same issue. I have a quadro k1200 Also using
USE_FP16=false.
So, I belive I did all the update requirements correctly. I…
@NickM-27 commented on GitHub (Feb 12, 2024):
I don't know why this would be happening. There were no reports during the beta / RC and it is not clear why something would be doing this unless the…
@BunpGhost commented on GitHub (Feb 13, 2024):
I don't know why this would be happening. There were no reports during the beta / RC and it is not clear why something would be doing this unless…
@NickM-27 commented on GitHub (Feb 13, 2024):
what is your drive version? this is a typical error that means the card has an out of date driver
@BunpGhost commented on GitHub (Feb 13, 2024):
what is your drive version? this is a typical error that means the card has an out of date driver
Thanks for the reply. It is on the…
@NateMeyer commented on GitHub (Feb 13, 2024):
I think that driver version is ok.
It's weird we're just seeing these issues with the Kx2 "Maxwell" Quadro cards. I wonder if there are issues…
@NickM-27 commented on GitHub (Feb 13, 2024):
That seems to be the consensus, compute 5.0 specifically are having issues
@NickM-27 commented on GitHub (Feb 8, 2024):
can you show the output of nvidia-smi
@hamishfagg commented on GitHub (Feb 9, 2024):
Sure thing, here it is: <img width="955" alt="image" src="https://github.com/blakeblackshear/frigate/assets/895845/75d32388-5d59-463c-9d19-999dedf84…
@hamishfagg commented on GitHub (Feb 8, 2024):
Hi,
I've tried re-generating yolov4-tiny-288, yolov4-tiny-416, yolov7-tiny-288, yolov7-tiny-416 models several times and haven't had any…
@DorjeDorf commented on GitHub (Feb 8, 2024):
I had a feeling that was too big of an omission, but had to try :) thanks for the hint.
@blakeblackshear commented on GitHub (Feb 8, 2024):
@NickM-27 commented on GitHub (Feb 8, 2024):
This is covered in the release notes. Previously frigate set the detect resolution to 1280x720 if the user did not set it but now frigate detects it…
@blakeblackshear commented on GitHub (Feb 8, 2024):
That icon will unselect all and select just the one label. Only takes one click rather than two with what you suggested.
@NickM-27 commented on GitHub (Feb 8, 2024):
We've not seen any other reports of this, the only way this would happen would be if the model was returning incorrect or unexpected values. Can you…
@paulcusick3 commented on GitHub (Feb 8, 2024):
Thanks. Missed it and did try and find it.