Open huyhoangle86 opened 3 years ago
@WongKinYiu please help
i have not used cpu for inference.
https://github.com/WongKinYiu/ScaledYOLOv4/blob/yolov4-csp/detect.py#L43 try to change .cuda() to .cpu()
@WongKinYiu No, I tried but it's not working still use >1GB of GPU lol
Hi, in detect.py I tried to set argument in --device = cpu to run only by CPU, but when I check the GPU status it still uses more than 1GB of my GPU as in the pic below . What happened ? How can I inference only on CPU? I did try to delve into the code but no luck
I'm using ScaledYOLOv4 CSP version