Deep Learning Computer Vision & YOLO

44 repos across 2 sub-areas

Deep learning frameworks and models for real-time object detection and computer vision tasks, centered on PyTorch implementations. The cluster contains numerous YOLO (You Only Look Once) variants and related detection architectures, alongside foundational vision models like DINO. Repositories span from core model implementations and training pipelines to inference optimization and practical applications, making this a comprehensive resource for practitioners building vision systems with modern deep learning approaches.