Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kadirnar/Minimal-Yolov6
YOLOv6: Single-stage Object Detection
https://github.com/kadirnar/Minimal-Yolov6
Last synced: 3 months ago
JSON representation
YOLOv6: Single-stage Object Detection
- Host: GitHub
- URL: https://github.com/kadirnar/Minimal-Yolov6
- Owner: kadirnar
- License: mit
- Created: 2022-06-26T13:21:07.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2022-07-05T14:01:25.000Z (over 2 years ago)
- Last Synced: 2024-08-02T01:17:38.886Z (7 months ago)
- Language: Python
- Homepage:
- Size: 3.1 MB
- Stars: 3
- Watchers: 2
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-yolo-object-detection - kadirnar/Minimal-Yolov6 - Yolov6?style=social"/> : Minimal-Yolov6. (Other Versions of YOLO)
README
YOLOv6: Single-stage Object Detection
### Installation
```shell
git clone --recurse-submodules https://github.com/kadirnar/YOLOv6.git
cd YOLOv6
pip install -r requirements.txt
```
### Inference
```shell
detection_model = Yolov6(
model_path="yolov6s.pt",
source="assert/highway.jpg",
img_size=1280,
conf_thres=0.3,
device="cpu",
)
detection_model.inference()
```
### Training
Single GPU
```shell
python YOLOv6/tools/train.py --batch 32 --conf configs/yolov6s.py --data data/coco.yaml --device 0
configs/yolov6n.py
```
Multi GPUs (DDP mode recommended)
```shell
python -m torch.distributed.launch --nproc_per_node 8 YOLOv6/tools/train.py --batch 256 --conf configs/yolov6s.py --data data/coco.yaml --device 0,1,2,3,4,5,6,7
configs/yolov6n.py
```
- conf: select config file to specify network/optimizer/hyperparameters
- data: prepare [COCO](http://cocodataset.org) dataset and specify dataset paths in data.yaml
### Evaluation
Reproduce mAP on COCO val2017 dataset
```shell
python YOLOv6/tools/eval.py --data data/coco.yaml --batch 32 --weights yolov6s.pt --task val
yolov6n.pt
```
### Deployment
* [ONNX](./deploy/ONNX)
* [OpenVINO](./deploy/OpenVINO)
### Tutorials
* [Train custom data](./docs/Train_custom_data.md)
* [Test speed](./docs/Test_speed.md)
## Benchmark
| Model | Size | mAPval
0.5:0.95 | SpeedV100
fp16 b32
(ms) | SpeedV100
fp32 b32
(ms) | SpeedT4
trt fp16 b1
(fps) | SpeedT4
trt fp16 b32
(fps) | Params
(M) | Flops
(G) |
| :-------------- | ----------- | :----------------------- | :------------------------------------ | :------------------------------------ | ---------------------------------------- | ----------------------------------------- | --------------- | -------------- |
| [**YOLOv6-n**](https://github.com/meituan/YOLOv6/releases/download/0.1.0/yolov6n.pt) | 416
640 | 30.8
35.0 | 0.3
0.5 | 0.4
0.7 | 1100
788 | 2716
1242 | 4.3
4.3 | 4.7
11.1 |
| [**YOLOv6-tiny**](https://github.com/meituan/YOLOv6/releases/download/0.1.0/yolov6t.pt) | 640 | 41.3 | 0.9 | 1.5 | 425 | 602 | 15.0 | 36.7 |
| [**YOLOv6-s**](https://github.com/meituan/YOLOv6/releases/download/0.1.0/yolov6s.pt) | 640 | 43.1 | 1.0 | 1.7 | 373 | 520 | 17.2 | 44.2 |
- Comparisons of the mAP and speed of different object detectors are tested on [COCO val2017](https://cocodataset.org/#download) dataset.
- Refer to [Test speed](./docs/Test_speed.md) tutorial to reproduce the speed results of YOLOv6.
- Params and Flops of YOLOv6 are estimated on deployed model.
- Speed results of other methods are tested in our environment using official codebase and model if not found from the corresponding official release.