Adding New Classes to a Trained YOLO Model Without Affecting Old Weights
Add new classes to a pre-trained YOLO model, or improve existing ones, without changing the predictions of the other classes, using the RefineDetectionTrainer.
Hello. I'm Mohammed Yasin.
I develop computer vision solutions for video analytics at the edge.
Learn how to prune and fine-tune YOLO models to boost efficiency, reduce size, and speed up inference. Add reidentification to Ultralytics without compromising latency using object-level features extracted from YOLO. Use Lightly to pretrain a YOLO backbone through self-supervised learning and then fine-tune it in Ultralytics. Boost your inference performance by exploiting Kalman filter predictions to interpolate detections for skipped frames.
Recent Posts
Pruning Ultralytics YOLO Models with NVIDIA Model Optimizer
Tracking with Efficient Re-Identification in Ultralytics
Pretrain YOLO Backbone Using Self-Supervised Learning With Lightly
More Posts
Boosting Inference FPS With Tracker Interpolated Detections
My Projects
View all »