Is Retinaface particularly slow to see a new image size for the first time? about pytorch_retinaface HOT 4 CLOSED

The slowest part will be the CUDNN optimization.
Every time it gets a new input size, it calculates the optimal instructions at run time. You can disable this feature by setting torch.backends.cudnn.benchmark = False

See: https://github.com/biubug6/Pytorch_Retinaface/blob/master/detect.py#L73

from pytorch_retinaface.

Probably generating the prior box + CUDNN optimising for different sized convolutions.

from pytorch_retinaface.

thanks, But I think generating the prior box for each picture should be independent. For images of the same size, each picture should take the same amount of time whether it is the first time or not.

from pytorch_retinaface.

Okay, thanks for your answer.

from pytorch_retinaface.