AG

icon location Bengaluru icon location An Embedded and ML enthusiast

Results 4 comments of AG

Decreasing number of resnet layers

I am able to make it to resnet-18 but mAPs are very low. I am figuring it out currently.

Training yolact on resnet18 and got some error

I am able to make it run but getting very slow training speed

Training yolact on resnet18 and got some error

Solution - Don't use torch1.12. Either upgrade or degrade the version of torch with cuda.

Backbone for yolact++

Hi @elfpattern , Have you also tried with resnet18? In above command, you have mentioned --config=yolact_resnet18_config but I can see your config.py does not contain resnet18 configuration. Also, what mAPs...