Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
| Date | Stars |
|---|---|
| 2026-07-24 | 3107 |
| 2026-07-25 | 3107 |
| 2026-07-28 | 3107 |
| 2026-07-30 | 3107 |
| 2026-08-06 | 3107 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <img src="https://s1.ax1x.com/2022/08/23/vcB3Pe.png"> [Documentation](https://github.com/jinfagang/yolov7) • [Installation Instructions](https://github.com/jinfagang/yolov7) • [Deployment](#deploy) • [Contributing](.github/CONTRIBUTING.md) • [Reporting Issues](https://github.com/jinfagang/yolov7/issues/new?assignees=&labels=&template=bug-report.yml) [](https://pypi.org/project/yolov7-d2/) [](https://pepy.tech/project/yolov7-d2) [](https://img.shields.io/github/downloads/jinfagang/yolov7/total?color=blue&label=Downloads&logo=github&logoColor=lightgrey) [](https://github.com/jinfagang/yolov7/issues?q=is%3Aopen+is%3Aissue+label%3A%22help+wanted%22) </div> > this is another yolov7 implementation based on detectron2, YOLOX, YOLOv6, YOLOv5, DETR, Anchor-DETR, DINO and some other SOTA detection models also supported. The ultimate goal of yolov7-d2 is to build a powerful weapon for **anyone** who wants a SOTA detector and train it **without pain**. It's extremly easy for users to build any **Multi-Head** models on yolov7-d2, for example, our E2E pose estimation is build on yolov7-d2 and works very well. Thanks for Aarohi's youtube vlog for guaidance of yolov7: https://www.youtube.com/watch?v=ag88beS_fvM , if you want a quick start, take a look at this nice introduction on yolov7 and detectron2. ## New version will release! **YOLOv7** v2.0 will be released soon! We will release our Convext-tiny YOLO arch model achieves mAP 43.9 with very low latency! Feature will be included in next version: - Support EfficientFormer backbone; - Support new YOLO2Go model, more lighter, much more faster and much more accurate; - Support MobileOne backbone; For more details, refer to [read the doc](https://yolov7.readthedocs.io/en/latest). Just **fork and star!**, you will be noticed once we release the new version! 🔥🔥🔥 Just another yolo variant implemented based on **`detectron2`**. But note that **YOLOv7 isn't meant to be a successor of yolo family, 7 is just a magic and lucky number. Instead, YOLOv7 extends yolo into many other vision tasks, such as instance segmentation, one-stage keypoints detection etc.**. The supported matrix in YOLOv7 are: - [x] YOLOv4 contained with CSP-Darknet53; - [x] YOLOv7 arch with resnets backbone; - [ ] YOLOv7 arch with resnet-vd backbone (likely as PP-YOLO), deformable conv, Mish etc; - [x] GridMask augmentation from PP-YOLO included; - [x] Mosiac transform supported with a custom datasetmapper; - [x] YOLOv7 arch Swin-Transformer support (higher accuracy but lower speed); - [ ] YOLOv7 arch Efficientnet + BiFPN; - [ ] YOLOv5 style positive samples selection, new coordinates coding style; - [x] RandomColorDistortion, RandomExpand, RandomCrop, RandomFlip; - [x] CIoU loss (DIoU, GIoU) and label smoothing (from YOLOv5 & YOLOv4); - [ ] YOLOF also included; - [x] YOLOv7 Res2net + FPN supported; - [x] Pyramid Vision Transformer v2 (PVTv2) supported; - [ ] WBF (Weighted Box Fusion), this works better than NMS, [link](https://github.com/ZFTurbo/Weighted-Boxes-Fusion); - [ ] YOLOX like head design and anchor design, also training support; - [x] YOLOX s,m,l backbone and PAFPN added, we have a new combination of YOLOX backbone and pafpn; - [x] YOLOv7 with Res2Net-v1d backbone, we **found res2net-v1d** have a better accuracy then darknet53; - [x] Added PPYOLOv2 PAN neck with SPP and dropblock; - [x] YOLOX arch added, now you can train YOLOX model (**anchor free yolo**) as well; - [x] DETR: transformer based detection model and **onnx export supported
Excerpt of 19,879 characters
Read on GitHub
MagicSource · Google
30
Bharat Ramanathan · Weights & Biases · India
20
CSTEZCAN · @TARSENS
7
Gyeongbo Sim · Naver Webtoon
4
3
3
2
1
Yonghye Kwon · MarkAny · South Korea
1
Sam Gao · DINQ · China
1
Hommoner
1
1
1
Jing Qiu · China
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8f965ab1fde81ab8, topic:object-detection, topic:yolo, desc:instance segmentation
matched fp:8f965ab1fde81ab8, topic:tensorrt, topic:onnx