zenjieli

Results 3 comments of zenjieli

It appears that the correct way to recover the coordinates is (x * image_width / 999, y * image_height / 999). You can verify this with the cat image above....

I agreed with @GTrui6 that many people probably use the default "--task dataloader" instead of "--task inference", so the resulting FPS is unrealistically high. I tried to reproduce the FPS...