184

GitHub - jinfagang/yolov7: 🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation...

 2 years ago
source link: https://github.com/jinfagang/yolov7
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.

This is the first and only (for now) YOLO family variant with transformers! and more advanced YOLO with multi-tasking such as detect & segmentation at the same time!

firefirefire Just another yolo variant implemented based on detectron2. Be note that YOLOv7 doesn't meant to be a successor of yolo family, 7 is just my magic and lucky number. In our humble opinion, a good opensource project must have these features:

  • It must be reproduceble;
  • It must be simple and understandable;
  • It must be build with the weapon of the edge;
  • It must have a good maintainance, listen to the voice from community;

However, we found many opensource detection framework such as YOLOv5, Efficientdet have their own weakness, for example, YOLOv5 is very good at reproduceable but really over-engineered, too many messy codes. What's more surprisingly, there were at least 20+ different version of re-implementation of YOLOv3-YOLOv4 in pytorch, 99.99% of them were totally wrong, either can u train your dataset nor make it mAP comparable with origin paper.(However, doesn't mean this work is totally right, use at your own risk.)

That's why we have this project! It's much more simpler to experiment different ARCH of YOLO build upon detectron2 with YOLOv7! Most importantly, more and more decent YOLO series model merged into this repo such as YOLOX (most decent in 2021). We also welcome any trick/experiment PR on YOLOv7, help us build it better and stronger!!. Please star it and fork it right now!.

The supported matrix in YOLOv7 are:

  • 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;
  • Mosiac transform supported with a custom datasetmapper;
  • 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!

what's more, there are some features awesome inside repo:

  • Almost all models can export to onnx;
  • Supports TensorRT deployment for DETR and other transformer models;
  • It will integrate with wanwu, a torch-free deploy framework run fastest on your target platform.

tipping_hand_man Results

YOLOv7 Instance Face & Detection

thinking Features

Some highlights of YOLOv7 are:

  • A simple and standard training framework for any detection && instance segmentation tasks, based on detectron2;
  • Supports DETR and many transformer based detection framework out-of-box;
  • Supports easy to deploy pipeline thought onnx.
  • This is the only framework support YOLOv4 + InstanceSegmentation in single stage style;
  • Easily plugin into transformers based detector;

We are strongly recommend you send PR if you have any further development on this project, the only reason for opensource it is just for using community power to make it stronger and further. It's very welcome for anyone contribute on any features!

raised_hands Tasks Want Community to Finish

  • train a hand detection model, with YOLOX;
  • add more instance segmentation models into YOLOv7;

sunglasses Rules

There are some rules you must follow to if you want train on your own dataset:

  • Rule No.1: Always set your own anchors on your dataset, using tools/compute_anchors.py, this applys to any other anchor-based detection methods as well (EfficientDet etc.);
  • Rule No.2: Keep a faith on your loss will goes down eventually, if not, dig deeper to find out why (but do not post issues repeated caused I might don't know either.).
  • Rule No.3: No one will tells u but it's real: do not change backbone easily, whole params coupled with your backbone, dont think its simple as you think it should be, also a Deeplearning engineer is not an easy work as you think, the whole knowledge like an ocean, and your knowledge is just a tiny drop of water...
  • Rule No.4: must using pretrain weights for transoformer based backbone, otherwise your loss will bump;

Make sure you have read rules before ask me any questions.

new News!

  • 2021.09.16: First transformer based DETR model added, will explore more DETR series models;
  • 2021.08.02: YOLOX arch added, you can train YOLOX as well in this repo;
  • 2021.07.25: We found YOLOv7-Res2net50 beat res50 and darknet53 at same speed level! 5% AP boost on custom dataset;
  • 2021.07.04: Added YOLOF and we can have a anchor free support as well, YOLOF achieves a better trade off on speed and accuracy;
  • 2021.06.25: this project first started.

person_with_probing_cane Installation && Quick Start

sunglasses Train

For training, quite simple, same as detectron2:

python train_net.py --config-file configs/coco/darknet53.yaml --num-gpus 8

If you want train YOLOX, you can using config file configs/coco/yolox_s.yaml. All support arch are:

  • YOLOX: anchor free yolo;
  • YOLOv7: traditional yolo with some explorations, mainly focus on loss experiments;
  • YOLOv7P: traditional yolo merged with decent arch from YOLOX;
  • YOLOMask: arch do detection and segmentation at the same time (tbd);
  • YOLOInsSeg: instance segmentation based on YOLO detection (tbd);

smiling_face_with_three_hearts Demo

Run a quick demo would be like:

python3 demo.py --config-file configs/wearmask/darknet53.yaml --input ./datasets/wearmask/images/val2017 --opts MODEL.WEIGHTS output/model_0009999.pth

an update based on detectron2 newly introduced LazyConfig system, run with a LazyConfig model using:

python3 demo_lazyconfig.py --config-file configs/new_baselines/panoptic_fpn_regnetx_0.4g.py --opts train.init_checkpoint=output/model_0004999.pth

Export ONNX && TensorRTT && TVM

  1. detr:
python export_onnx.py --config-file detr/config/file

this works has been done, inference script included inside tools.

  1. AnchorDETR:

anchorDETR also supported training and exporting to ONNX.

More Advanced YOLO

Here we show some highlights on multi-tasking:

Performance

Here is a dedicated performance compare with other packages.

Some Tiny Object Datasets supported

Detection Results

Dicussion Group

Wechat QQ

  • if wechat expired, please contact me update via github issue. group for general discussion, not only for yolov7.

Some Exp Visualizations

  1. GridMask

    Our GridMask augmentation also supports 2 modes.

  2. Mosaic

    Our Mosaic support any size and any any image numbers!

    new: we merged another mosiac implementation from YOLOX, this version will do random pespective:

License

Code released under GPL license. Please pull request to this source repo before you make your changes public or commercial usage. All rights reserved by Lucas Jin.


About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK