lucasjinreal/yolov7_d2
An object detection and instance segmentation library implementing YOLOv7, DETR, and other vision transformers with TensorRT acceleration.
Velocity · 7d
+1.7
★ / day
Trend
→steady
star history
This repository provides a YOLOv7 implementation built on detectron2, combining it with YOLOX, YOLOv6, DETR, Anchor-DETR, and DINO detection models. It supports object detection, instance segmentation, face detection, and pose estimation through a multi-head architecture. TensorRT integration enables accelerated inference. Users can build custom detection models without extensive configuration.