YOLOv9

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

Performance

MS COCO

| Model | Test Size | AP^val | AP₅₀^val | AP₇₅^val | Param. | FLOPs | | :-- | :-: | :-: | :-: | :-: | :-: | :-: | | YOLOv9-T | 640 | 38.3% | 53.1% | 41.3% | 2.0M | 7.7G | | YOLOv9-S | 640 | 46.8% | 63.4% | 50.7% | 7.1M | 26.4G | | YOLOv9-M | 640 | 51.4% | 68.1% | 56.1% | 20.0M | 76.3G | | YOLOv9-C | 640 | 53.0% | 70.2% | 57.8% | 25.3M | 102.1G | | YOLOv9-E | 640 | 55.6% | 72.8% | 60.6% | 57.3M | 189.0G | <!-- | YOLOv9 (ReLU) | 640 | 51.9% | 69.1% | 56.5% | 25.3M | 102.1G | -->

Useful Links

Expand

Custom training: https://github.com/WongKinYiu/yolov9/issues/30#issuecomment-1960955297 ONNX export: https://github.com/WongKinYiu/yolov9/issues/2#issuecomment-1960519506 https://github.com/WongKinYiu/yolov9/issues/40#issue-2150697688 https://github.com/WongKinYiu/yolov9/issues/130#issue-2162045461 ONNX export for segmentation: https://github.com/WongKinYiu/yolov9/issues/260#issue-2191162150 TensorRT inference: https://github.com/WongKinYiu/yolov9/issues/143#issuecomment-1975049660 https://github.com/WongKinYiu/yolov9/issues/34#issue-2150393690 https://github.com/WongKinYiu/yolov9/issues/79#issue-2153547004 https://github.com/WongKinYiu/yolov9/issues/143#issue-2164002309 QAT TensorRT: https://github.com/WongKinYiu/yolov9/issues/327#issue-2229284136 https://github.com/WongKinYiu/yolov9/issues/253#issue-2189520073 TFLite: https://github.com/WongKinYiu/yolov9/issues/374#issuecomment-2065751706 OpenVINO: https://github.com/WongKinYiu/yolov9/issues/164#issue-2168540003 C# ONNX inference: https://github.com/WongKinYiu/yolov9/issues/95#issue-2155974619 C# OpenVINO inference: https://github.com/WongKinYiu/yolov9/issues/95#issuecomment-1968131244 OpenCV: https://github.com/WongKinYiu/yolov9/issues/113#issuecomment-1971327672 Hugging Face demo: https://github.com/WongKinYiu/yolov9/issues/45#issuecomment-1961496943 CoLab demo: https://github.com/WongKinYiu/yolov9/pull/18 ONNXSlim export: https://github.com/WongKinYiu/yolov9/pull/37 YOLOv9 ROS: https://github.com/WongKinYiu/yolov9/issues/144#issue-2164210644 YOLOv9 ROS TensorRT: https://github.com/WongKinYiu/yolov9/issues/145#issue-2164218595 YOLOv9 Julia: https://github.com/WongKinYiu/yolov9/issues/141#issuecomment-1973710107 YOLOv9 MLX: https://github.com/WongKinYiu/yolov9/issues/258#issue-2190586540 YOLOv9 StrongSORT with OSNet: https://github.com/WongKinYiu/yolov9/issues/299#issue-2212093340 YOLOv9 ByteTrack: https://github.com/WongKinYiu/yolov9/issues/78#issue-2153512879 YOLOv9 DeepSORT: https://github.com/WongKinYiu/yolov9/issues/98#issue-2156172319 YOLOv9 counting: https://github.com/WongKinYiu/yolov9/issues/84#issue-2153904804 YOLOv9 face detection: https://github.com/WongKinYiu/yolov9/issues/121#issue-2160218766 YOLOv9 segmentation onnxruntime: https://github.com/WongKinYiu/yolov9/issues/151#issue-2165667350 Comet logging: https://github.com/WongKinYiu/yolov9/pull/110 MLflow logging: https://github.com/WongKinYiu/yolov9/pull/87 AnyLabeling tool: https://github.com/WongKinYiu/yolov9/issues/48#issue-2152139662 AX650N deploy: https://github.com/WongKinYiu/yolov9/issues/96#issue-2156115760 Conda environment: https://github.com/WongKinYiu/yolov9/pull/93 AutoDL docker environment: https://github.com/WongKinYiu/yolov9/issues/112#issue-2158203480

Installation

Docker environment (recommended)

Expand

``` shell

create the docker container, you can change the share memory size if you have more.

nvidia-docker run --name yolov9 -it -v yourcocopath/:/coco/ -v yourcodepath/:/yolov9 --shm-size=64g nvcr.io/nvidia/pytorch:21.11-py3

apt install required packages

apt update apt install -y zip htop screen libgl1-mesa-glx

pip install required packages

pip install seaborn thop

go to code folder

cd /yolov9 ```

Evaluation

yolov9-c-converted.pt yolov9-e-converted.pt yolov9-c.pt yolov9-e.pt gelan-c.pt gelan-e.pt

``` shell

evaluate converted yolov9 models

python val.py --data data/coco.yaml --img 640 --batch 32 --conf 0.001 --iou 0.7 --device 0 --weights './yolov9-c-converted.pt' --save-json --name yolov9cc640val

evaluate yolov9 models

python valdual.py --data data/coco.yaml --img 640 --batch 32 --conf 0.001 --iou 0.7 --device 0 --weights './yolov9-c.pt' --save-json --name yolov9c640val

evaluate gelan models

python val.py --data data/coco.yaml --img 640 --batch 32 --conf 0.001 --iou 0.7 --device 0 --weights './gelan-c.pt' --save-json --name gelanc640_val

```

You will get the results:

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.530 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.702 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.578 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.362 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.585 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.693 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.392 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.652 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.702 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.541 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.760 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.844

Training

Data preparation

shell bash scripts/get_coco.sh

• Download MS COCO dataset images (train, val, test) and labels. If you have previously used a different version of YOLO, we strongly recommend that you delete train2017.cache and val2017.cache files, and redownload labels

Single GPU training

``` shell

train yolov9 models

python train_dual.py --workers 8 --device 0 --batch 16 --data data/coco.yaml --img 640 --cfg models/detect/yolov9-c.yaml --weights '' --name yolov9-c --hyp hyp.scratch-high.yaml --min-items 0 --epochs 500 --close-mosaic 15

train gelan models

python train.py --workers 8 --device 0 --batch 32 --data data/coco.yaml --img 640 --cfg models/detect/gelan-c.yaml --weights '' --name gelan-c --hyp hyp.scratch-high.yaml --min-items 0 --epochs 500 --close-mosaic 15

```

Multiple GPU training

``` shell

train yolov9 models

python -m torch.distributed.launch --nprocpernode 8 --masterport 9527 traindual.py --workers 8 --device 0,1,2,3,4,5,6,7 --sync-bn --batch 128 --data data/coco.yaml --img 640 --cfg models/detect/yolov9-c.yaml --weights '' --name yolov9-c --hyp hyp.scratch-high.yaml --min-items 0 --epochs 500 --close-mosaic 15

train gelan models

python -m torch.distributed.launch --nprocpernode 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch 128 --data data/coco.yaml --img 640 --cfg models/detect/gelan-c.yaml --weights '' --name gelan-c --hyp hyp.scratch-high.yaml --min-items 0 --epochs 500 --close-mosaic 15

```

Re-parameterization

See reparameterization.ipynb.

Inference

``` shell

inference converted yolov9 models

python detect.py --source './data/images/horses.jpg' --img 640 --device 0 --weights './yolov9-c-converted.pt' --name yolov9cc640detect

inference yolov9 models

python detectdual.py --source './data/images/horses.jpg' --img 640 --device 0 --weights './yolov9-c.pt' --name yolov9c640detect

inference gelan models

python detect.py --source './data/images/horses.jpg' --img 640 --device 0 --weights './gelan-c.pt' --name gelancc640detect

```

Citation

@article{wang2024yolov9, title={{YOLOv9}: Learning What You Want to Learn Using Programmable Gradient Information}, author={Wang, Chien-Yao and Liao, Hong-Yuan Mark}, booktitle={arXiv preprint arXiv:2402.13616}, year={2024} }

@article{chang2023yolor, title={{YOLOR}-Based Multi-Task Learning}, author={Chang, Hung-Shuo and Wang, Chien-Yao and Wang, Richard Robert and Chou, Gene and Liao, Hong-Yuan Mark}, journal={arXiv preprint arXiv:2309.16921}, year={2023} }

Teaser

Parts of code of YOLOR-Based Multi-Task Learning are released in the repository.

Object Detection

gelan-c-det.pt

object detection

``` shell

coco/labels/{split}/*.txt

bbox or polygon (1 instance 1 line)

python train.py --workers 8 --device 0 --batch 32 --data data/coco.yaml --img 640 --cfg models/detect/gelan-c.yaml --weights '' --name gelan-c-det --hyp hyp.scratch-high.yaml --min-items 0 --epochs 300 --close-mosaic 10 ```

| Model | Test Size | Param. | FLOPs | AP<sup>box</sup> | | :-- | :-: | :-: | :-: | :-: | | GELAN-C-DET | 640 | 25.3M | 102.1G |52.3% | | YOLOv9-C-DET | 640 | 25.3M | 102.1G | 53.0% |

Instance Segmentation

gelan-c-seg.pt

object detection instance segmentation

``` shell

coco/labels/{split}/*.txt

polygon (1 instance 1 line)

python segment/train.py --workers 8 --device 0 --batch 32 --data coco.yaml --img 640 --cfg models/segment/gelan-c-seg.yaml --weights '' --name gelan-c-seg --hyp hyp.scratch-high.yaml --no-overlap --epochs 300 --close-mosaic 10 ```

| Model | Test Size | Param. | FLOPs | AP<sup>box</sup> | AP<sup>mask</sup> | | :-- | :-: | :-: | :-: | :-: | :-: | | GELAN-C-SEG | 640 | 27.4M | 144.6G | 52.3% | 42.4% | | YOLOv9-C-SEG | 640 | 27.4M | 145.5G | 53.3% | 43.5% |

Panoptic Segmentation

gelan-c-pan.pt

object detection instance segmentation semantic segmentation stuff segmentation panoptic segmentation

``` shell

coco/labels/{split}/*.txt

polygon (1 instance 1 line)

coco/stuff/{split}/*.txt

polygon (1 semantic 1 line)

python panoptic/train.py --workers 8 --device 0 --batch 32 --data coco.yaml --img 640 --cfg models/panoptic/gelan-c-pan.yaml --weights '' --name gelan-c-pan --hyp hyp.scratch-high.yaml --no-overlap --epochs 300 --close-mosaic 10 ```

| Model | Test Size | Param. | FLOPs | AP<sup>box</sup> | AP<sup>mask</sup> | mIoU<sub>164k/10k</sub><sup>semantic</sup> | mIoU<sup>stuff</sup> | PQ<sup>panoptic</sup> | | :-- | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | | GELAN-C-PAN | 640 | 27.6M | 146.7G | 52.6% | 42.5% | 39.0%/48.3% | 52.7% | 39.4% | | YOLOv9-C-PAN | 640 | 28.8M | 187.0G | 52.7% | 43.0% | 39.8%/- | 52.2% | 40.5% |

Image Captioning (not yet released)

object detection instance segmentation semantic segmentation stuff segmentation panoptic segmentation image captioning

``` shell

coco/labels/{split}/*.txt

polygon (1 instance 1 line)

coco/stuff/{split}/*.txt

polygon (1 semantic 1 line)

coco/annotations/*.json

json (1 split 1 file)

python caption/train.py --workers 8 --device 0 --batch 32 --data coco.yaml --img 640 --cfg models/caption/gelan-c-cap.yaml --weights '' --name gelan-c-cap --hyp hyp.scratch-high.yaml --no-overlap --epochs 300 --close-mosaic 10 ```

| Model | Test Size | Param. | FLOPs | AP<sup>box</sup> | AP<sup>mask</sup> | mIoU<sub>164k/10k</sub><sup>semantic</sup> | mIoU<sup>stuff</sup> | PQ<sup>panoptic</sup> | BLEU@4<sup>caption</sup> | CIDEr<sup>caption</sup> | | :-- | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | | GELAN-C-CAP | 640 | 47.5M | - | 51.9% | 42.6% | 42.5%/- | 56.5% | 41.7% | 38.8 | 122.3 | | YOLOv9-C-CAP | 640 | 47.5M | - | 52.1% | 42.6% | 43.0%/- | 56.4% | 42.1% | 39.1 | 122.0 | <!--| YOLOR-MT | 640 | 79.3M | - | 51.0% | 41.7% | -/49.6% | 55.9% | 40.5% | 35.7 | 112.7 |-->

Acknowledgements

Expand

* [https://github.com/AlexeyAB/darknet](https://github.com/AlexeyAB/darknet) * [https://github.com/WongKinYiu/yolor](https://github.com/WongKinYiu/yolor) * [https://github.com/WongKinYiu/yolov7](https://github.com/WongKinYiu/yolov7) * [https://github.com/VDIGPKU/DynamicDet](https://github.com/VDIGPKU/DynamicDet) * [https://github.com/DingXiaoH/RepVGG](https://github.com/DingXiaoH/RepVGG) * [https://github.com/ultralytics/yolov5](https://github.com/ultralytics/yolov5) * [https://github.com/meituan/YOLOv6](https://github.com/meituan/YOLOv6)