karthikiitm87

Unable to replicate the results in DG-YOLO paper

1

I am not sure why I am unable to replicate the results in DG-YOLO paper. I have used the given checkpoint and used the test.py code with the following command....

Erroneous pruning of Swin Transformers when prune_hf_swin.py is used with pruning ratios < 0.5

1

I was experimenting with prune_hf_swin.py to analyse the impact of various pruning ratios on the performance of the model. However, I always get errors if I use pruning ratios less...