1 dépôt
Extraction of features specifically from the boundaries of bounding boxes for refinement.
Distinct from Computer Vision Features: Distinct from general Computer Vision Features by focusing specifically on boundary/border sampling of RoIs.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Border Feature Extraction. Refine with filters or upvote what's useful.
mmcv is a foundation library for computer vision based on PyTorch. It provides a comprehensive system for constructing convolutional neural networks, a toolkit for image and video preprocessing, and a collection of high-performance deep learning vision operators. The project is distinguished by its hardware-accelerated kernels for complex operations such as deformable convolutions and region pooling. It features a configuration-driven framework that allows for the dynamic instantiation of network layers and the registration of custom modules without modifying code. The library covers a broad
Samples and pools features along bounding box boundaries using bilinear interpolation to refine object detection.