LukeAI

can confirm no segfaults! no idea why it's different.

I've written inference code and after some experimenting everything is working, (ie. I get accurate looking bounding boxes) except that the class values are always reported as `0` when they...

hey thanks! Turned out to be unrelated mistake in the forward function, have updated the linked gist to correct code in case it helps somebody.

@NatanBagrov have implemented https://github.com/Deci-AI/super-gradients/issues/1161

yeah a call is fine

Hi Harpreet, Sorry to let you down short notice but I'm not going to be able to make the 11.30 call, something has come up. I can reschedule. Luke ________________________________...

Just use yolov7/8 ? ________________________________ From: hoangduyloc ***@***.***> Sent: 30 January 2021 3:58 PM To: WongKinYiu/ScaledYOLOv4 ***@***.***> Cc: Subscribed ***@***.***> Subject: Re: [WongKinYiu/ScaledYOLOv4] Can't use mish-cuda in cuda 11.1 (#119)...

depthwise convolution models like efficientnet are very slow on GPU. If you need GPU realtime, consider yolov3-spp or csresnext50

These sound great! I'd definitely appreciate these facilities in the main repo.

@xuanandsix why not accept this PR to fix this bug https://github.com/xuanandsix/CLRNet-onnxruntime-and-tensorrt-demo/issues/3