Manu B.N
This code is a piece of trash. Waste of time
[extract_kmedoid_points](https://github.com/SysCV/sam-pt/blob/main/sam_pt/utils/query_points.py#L62-L99) only gives you the +ve points. How to get the -ve points using the same algorithm ?
I could fix the error by by changing the teacher model name in 'configs/strategies/distill/resnet_dist.yaml' from 'tv_resnet34' to 'resnet34'. Now the student model trains well. But I don't know how to...
Yes on a resnet50 from pytorch, it give a validation accuracy of 0.93. I dont know how using DSIT_KD the validation accuracy is so poor
Ok. Thanks for letting me know.
 I did all of the above mentioned for image size 384, but I still get a very low accuracy for the teacher.
Please upload the model at the earliest !
Where are the pre trained models ?
How did you fix this issue? How to correctly mention the path ?
How did you solve this issue ?