It is mentioned in the YOLOv1 paper that the authors pretrained their network on ImageNet with a resolution of (224,224), but while training for detection tasks, they use a resolution of (448,448). Why not pretrain the classification head on this larger resolution and use that instead?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.