Retrieving Object-Level Features From YOLO
Extract the object-level features from YOLO for downstream tasks without extra overhead.
I write my discoveries here.
Extract the object-level features from YOLO for downstream tasks without extra overhead.
Implement class balancing in Ultralytics using a weighted dataloader and improve the performance of minority class.
Get over 10% more mAP in small object detection by exploiting YOLOv8 pose models while training.
Add additional classes to pre-trained YOLOv8 model without affecting the confidences on the existing classes.
Some useful tricks and hacks I learnt while using MMDetection for my research work.
A quick monkey patching technique to modify MMDetection 3.1.0 to return class probabilities.
A useful trick to debug deeply embedded functions and methods in Python.
Guide to download background images using COCOAPI.