hi,professor:
i have a weights file trained in darknet, with cfg resolution 608x608, when i use tkDNN to infer, think about speed, i may convert 416x416 tensorRT engine, so , can i just use the trained weights in 608*608? is there any modify should i do? please help!
hi,professor: i have a weights file trained in darknet, with cfg resolution 608x608, when i use tkDNN to infer, think about speed, i may convert 416x416 tensorRT engine, so , can i just use the trained weights in 608*608? is there any modify should i do? please help!