发布时间:2022-08-19 12:15
关注并星标
从此不迷路
计算机视觉研究院
公众号ID|ComputerVisionGzq
学习群|扫码在主页获取加入方式
计算机视觉研究院专栏
作者:Edison_G
请注意,这里的7,不是下一代YOLO,而是一个幸运数字,姑且可以看作是一个代号。它的目的是让YOLO全面开花,不仅仅只是做目标检测。也不是简单的加一个semantic head做分割,而是做一个体系的目标检测积木模块,即插即用,使之能够更简单的做复杂的上层任务,比如多个分类head,实例分割,甚至是加上姿态检测等等。
转自《知乎——金天》
链接:https://zhuanlan.zhihu.com/p/464007111
目前支持的东西就这么一些,现列举一些大家可能感兴趣的:
支持GridMask,Mosiac的数据增强,而且可以可视化;
支持YOLOX(很强),而且部署方式比原版更方便,可训练,官方不是唯一可选;
支持YOLOv7+实例分割,是SingleStage的方式,目前用的是OrienMaskHead,未来可能增加更多方式;
支持DETR,AnchorDETR等transformer,这是独一无二的,在一个框架里面同时被支持;
YOLOv4 contained with CSP-Darknet53;
YOLOv7 arch with resnets backbone;
YOLOv7 arch with resnet-vd backbone (likely as PP-YOLO), deformable conv, Mish etc;
GridMask augmentation from PP-YOLO included;
YOLOv7 arch Swin-Transformer support (higher accuracy but lower speed);
YOLOv7 arch Efficientnet + BiFPN;
YOLOv5 style positive samples selection, new coordinates coding style;
RandomColorDistortion, RandomExpand, RandomCrop, RandomFlip;
CIoU loss (DIoU, GIoU) and label smoothing (from YOLOv5 & YOLOv4);
YOLOF also included;
YOLOv7 Res2net + FPN supported;
Pyramid Vision Transformer v2 (PVTv2) supported;
WBF (Weighted Box Fusion), this works better than NMS, link;
YOLOX like head design and anchor design, also training support;
YOLOX s,m,l backbone and PAFPN added, we have a new combination of YOLOX backbone and pafpn;
YOLOv7 with Res2Net-v1d backbone, we found res2net-v1d have a better accuracy then darknet53;
Added PPYOLOv2 PAN neck with SPP and dropblock;
YOLOX arch added, now you can train YOLOX model (anchor free yolo) as well;
DETR: transformer based detection model and onnx export supported, as well as TensorRT acceleration;
AnchorDETR: Faster converge version of detr, now supported!