You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello@fcakyon, I am using/sahi main/demo/reference_ for_ Mmdetection.ipynb is used to infer my mmdet model. When I use my mmdet model and the official dataset of Coco, Sahi's inference performance improves. However, when I use my own dataset (with only one category and the original image being a grayscale image), Sahi's inference performance is not as good as the inference in mmdet. What is the reason for this? Do you need to adjust any parameters? We look forward to your reply.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello@fcakyon, I am using/sahi main/demo/reference_ for_ Mmdetection.ipynb is used to infer my mmdet model. When I use my mmdet model and the official dataset of Coco, Sahi's inference performance improves. However, when I use my own dataset (with only one category and the original image being a grayscale image), Sahi's inference performance is not as good as the inference in mmdet. What is the reason for this? Do you need to adjust any parameters? We look forward to your reply.
Beta Was this translation helpful? Give feedback.
All reactions