1 个仓库
Utilities that transform computer vision model predictions into a standardized format for interoperability.
Distinct from Model Output Formatting: Focuses on computer vision detection/classification outputs rather than language model text schemas.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Computer Vision Normalizers. Refine with filters or upvote what's useful.
Supervision is a computer vision toolset for normalizing model outputs, managing datasets, and visualizing annotations. It provides a framework to convert predictions from various classification and detection models into a standardized data format to ensure interoperability across different computer vision pipelines. The library features a post-processor for filtering, counting, and tracking detected objects across image frames and video streams. It includes capabilities for large image tiling to improve the detection of small objects and tools for assigning persistent identities to objects t
Provides a framework to convert predictions from diverse computer vision models into a standardized data format.