1 dépôt
Awesome GitHub RepositoriesInference Result Caches
Persistent storage of pre-computed model detections and embeddings to accelerate evaluation cycles.
Distinct from Persistent Binary Caches: Distinct from Persistent Binary Caches: specifically caches AI inference outputs like bounding boxes and embeddings.
Explore 1 awesome GitHub repository matching data & databases · Inference Result Caches. Refine with filters or upvote what's useful.
Awesome Inference Result Caches GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- mikel-brostrom/boxmot
mikel-brostrom/boxmot
8,212Voir sur GitHubBoxmot is a multi-object tracking framework designed to follow multiple objects across video frames using motion and appearance algorithms to maintain consistent identities. It functions as a system for tracking objects with specific orientations using rotated bounding boxes and corresponding intersection-over-union computations. The project includes a re-identification model optimizer that converts neural networks into formats for hardware-accelerated execution. It also features an evolutionary hyperparameter tuner that iteratively mutates tracker settings to maximize accuracy for specific d
Stores pre-computed bounding boxes and feature vectors in local files to avoid redundant inference during evaluation.
Pythonboosttrackbotsortbytetrack
