Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.6%) to scientific vocabulary
Repository
yolov8 track with distillation
Basic Info
- Host: GitHub
- Owner: TernenceLopez
- License: gpl-3.0
- Language: Python
- Default Branch: main
- Size: 61.4 MB
Statistics
- Stars: 5
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
YoloV8 Detect and Track
requirement:
```python ultralytics==8.0.98
val ------------------------------------------------------------------
pycocotools tabulate
gitpython tensorboard numpy==1.23.1 # otherwise issues with track eval
StrongSORT ------------------------------------------------------------------
easydict
torchreid -------------------------------------------------------------------
gdown
OCSORT ----------------------------------------------------------------------
filterpy
Export ----------------------------------------------------------------------
onnx>=1.12.0 # ONNX export onnxsim>=0.4.1 # ONNX simplifier nvidia-pyindex # TensorRT export nvidia-tensorrt # TensorRT export openvino-dev>=2022.3 # OpenVINO export onnx2tf>=1.10.0
Hyperparam search -----------------------------------------------------------
optuna plotly # for hp importance and pareto front plots kaleido joblib ```
Validation
1. track.py
只能实现 ocsort 的跟踪算法，实现细节在 ./trackers 目录
commandline
mkdir ./valid_utils
cd ./valid_utils
mkdir ./data
MOT17 数据集存放到 ./valid_utils/data 目录
权重文件存放到 ./weight 目录
运行结果存放到 ./runs/val 及 ./val_utils/data/trackers/mot_challenge 目录
2. examples/val.py
能实现 'strongsort, ocsort', 'deepocsort算法，实现细节在 boxmot目录
shell
$ python3 val.py --tracking-method strongsort --benchmark MOT16
--tracking-method ocsort --benchmark MOT17
--tracking-method ocsort --benchmark <your-custom-dataset>
MOT17 数据集存放到 ./examples/val_utils/data 目录
权重文件存放到 ./examples/weights 目录
运行结果存放到 ./examples/runs/val 及 ./examples/val_utils/data/trackers/mot_challenge 目录
项目完善中ing...... 完善之后会整理出一个文档
Cite:
@software{Jocher_Ultralytics_YOLO_2023,
author = {Jocher, Glenn and Chaurasia, Ayush and Qiu, Jing},
license = {AGPL-3.0},
month = jan,
title = {{Ultralytics YOLO}},
url = {https://github.com/ultralytics/ultralytics},
version = {8.0.0},
year = {2023}
}
@software{Brostrom_Real-time_multi-object_segmentation,
author = {Broström, Mikel},
doi = {https://zenodo.org/record/7629840},
license = {AGPL-3.0},
title = {{Real-time multi-object, segmentation and pose tracking using Yolov8 with DeepOCSORT and LightMBN}},
url = {https://github.com/mikel-brostrom/yolov8_tracking},
version = {8.0}
}
Owner
- Name: elvis
- Login: TernenceLopez
- Kind: user
- Repositories: 1
- Profile: https://github.com/TernenceLopez
Citation (CITATION.cff)
cff-version: 1.2.0
preferred-citation:
type: software
message: "If you use Yolov8 StrongSORT OSNet, please cite it as below."
authors:
- family-names: Broström
given-names: Mikel
title: "Real-time multi-object tracking and segmentation using Yolov8 with StrongSORT and OSNet"
version: 8.0
doi: https://zenodo.org/record/7629840
date-released: 2023-2
license: GPL-3.0
url: "https://github.com/mikel-brostrom/yolov8_tracking"
GitHub Events
Total
Last Year
Dependencies
- actions/checkout v3 composite
- actions/setup-python v4 composite
- actions/stale v3 composite
- nvcr.io/nvidia/pytorch 22.11-py3 build
- pytorch/pytorch latest build
- Pillow >=7.1.2
- PyYAML >=5.3.1
- matplotlib >=3.2.2
- numpy >=1.18.5
- opencv-python >=4.6.0
- pandas >=1.1.4
- psutil *
- pyserial *
- requests >=2.23.0
- scipy >=1.4.1
- seaborn >=0.11.0
- tensorboard >=2.4.1
- thop >=0.1.1
- torch >=1.7.0
- torchvision >=0.8.1
- tqdm >=4.64.0
- ultralytics >=8.0.39
- wheel >=0.38.0
- numpy ==1.18.1
- scipy ==1.4.1
- Pillow ==8.1.2
- matplotlib ==3.2.1
- numpy ==1.18.1
- opencv_python ==4.4.0.46
- pycocotools ==2.0.2
- pytest ==6.0.1
- scikit_image ==0.16.2
- scipy ==1.4.1
- tabulate *
- tqdm ==4.64.0