Ash

icon company @sekilab icon location Boston, Massachusetts icon location Research Scientist (Computer Vision) in Tokyo Past: IIT, UTokyo, NASA JPL, MIT

Results 5 comments of Ash

Getting Nan loss while training

@super-wcg Yes, I solved the problem of getting NaN Loss. It was due to the error in the coordinates. The following things were giving NaN loss 1.Coordinates out of the...

Getting Nan loss while training

@1csu What's the size of your image?

Distributed run asks for existing best weights when specifying "device='0,1,2,3'" in model.train before initial training run

I am also facing the same issue. It is asking for best.pt file.

Add Weights and Bias support back in

Please add W&B back! It is necessary.

Yolo Tiny

@jaydubal Do you need a pre-trained model for YOLOv3-tiny? Can you send me the project link?