Data

Tools

Indexes

Applications

Experiments

Open Source Science

yolov8-face

YOLOv8-Face in Pytorch and ONNX

https://github.com/clibdev/yolov8-face

Science Score: 44.0%

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
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (5.7%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

YOLOv8-Face in Pytorch and ONNX

Basic Info
  • Host: GitHub
  • Owner: clibdev
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 3.77 MB
Statistics
  • Stars: 3
  • Watchers: 0
  • Forks: 1
  • Open Issues: 0
  • Releases: 1
Created about 3 years ago · Last pushed over 1 year ago
Metadata Files
Readme Contributing License Citation Security

README.md

Fork of derronqi/yolov8-face

Differences between original repository and fork:

  • Compatibility with PyTorch >=2.5. (🔥)
  • Original pretrained models from GitHub releases page. (🔥)
  • YOLOv8-Lite-t-Face and YOLOv8-Lite-s-Face compatibility fixes.
  • Sample script detect.py for inference.
  • Sample script export.py to export model to ONNX format.
  • The following deprecations has been fixed:
    • DeprecationWarning: 'np.float' is a deprecated alias for builtin 'float'.
    • FutureWarning: You are using 'torch.load' with 'weights_only=False'.
    • FutureWarning: Cython directive 'language_level' not set.
    • Cython Warning: Using deprecated NumPy API.

Installation

shell pip install -r requirements.txt

Pretrained models

  • Download links:

| Method | Model Size (MB) | weights | SHA-256 | |--------------------|-----------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------| | YOLOv8-Lite-t-Face | 5.1
1.2 | PyTorch
ONNX | bed8216edcff10fb6e3e906ae1ae77d6671b3cc3c810906635d5c76f25fd4b42
971ba0be8f9bbea0f824c52ff68adff88ef3477e22d794c4853250a5fb6dba2d | | YOLOv8-Lite-s-Face | 15.3
3.7 | PyTorch
ONNX | 82a456c2f307d054e62c5f4898005cf85f7d5a00ad482ccd41b11910f36d04dc
4e6b0b024ff068651f590e2435e46f069dc8cdcfd373c28598843f9408dba462 | | YOLOv8n-Face | 6.1
11.8 | PyTorch
ONNX | d545bf1add5aa736a4febac4f4f9245a6d596cd0fe70d5d57989fe0cb9e626ca
af09683be4937ebe23e9da0346cbf46cd937b73ed5fac986e6205e6c7cdd2c25 |

  • Evaluation results on WIDERFace dataset:

| Method | Test Size | Easy | Medium | Hard | |--------------------|-----------|------|--------|------| | YOLOv8-Lite-t-Face | 640 | 90.4 | 87.7 | 73.3 | | YOLOv8-Lite-s-Face | 640 | 93.4 | 91.2 | 78.6 | | YOLOv8n-Face | 640 | 94.5 | 92.2 | 79.0 |

Inference

shell python detect.py --weights yolov8n-face-derronqi.pt --source ultralytics/assets/bus.jpg --save-img

WIDERFace evaluation

shell python test_widerface.py --weights yolov8n-face-derronqi.pt --dataset_folder data/widerface/val/images/ shell cd widerface_evaluate shell python setup.py build_ext --inplace shell python evaluation.py

Export to ONNX format

shell pip install onnx shell python export.py --weights yolov8n-face-derronqi.pt

Owner

  • Login: clibdev
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
preferred-citation:
  type: software
  message: If you use this software, please cite it as below.
  authors:
  - family-names: Jocher
    given-names: Glenn
    orcid: "https://orcid.org/0000-0001-5950-6979"
  - family-names: Chaurasia
    given-names: Ayush
    orcid: "https://orcid.org/0000-0002-7603-6750"
  - family-names: Qiu
    given-names: Jing
    orcid: "https://orcid.org/0000-0003-3783-7069"
  title: "YOLO by Ultralytics"
  version: 8.0.0
  # doi: 10.5281/zenodo.3908559  # TODO
  date-released: 2023-1-10
  license: GPL-3.0
  url: "https://github.com/ultralytics/ultralytics"

GitHub Events

Total
  • Watch event: 3
  • Push event: 2
Last Year
  • Watch event: 3
  • Push event: 2

Dependencies

docker/Dockerfile docker
  • pytorch/pytorch 2.0.0-cuda11.7-cudnn8-runtime build
requirements.txt pypi
  • Cython >=0.29.35
  • PyYAML >=6.0.0
  • opencv-python >=4.7.0
  • psutil >=5.9.0
  • scipy >=1.10.0
  • seaborn >=0.12.0
  • thop >=0.1.1
  • torch >=2.0.0
  • torchvision >=0.15.0
  • tqdm >=4.65.0
setup.py pypi
widerface_evaluate/setup.py pypi