chess-pieces-detection-yolov5
https://github.com/sebastienjacquemart-ai/chess-pieces-detection-yolov5
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○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 (6.0%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: sebastienjacquemart-AI
- License: agpl-3.0
- Language: Python
- Default Branch: main
- Size: 36 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
TODO: Yolov9?? Add some theory about yolo-network
Dataset used
https://public.roboflow.com/object-detection/chess-full/24
How to configure environment?
Install the dependencies: !pip install -r requirements.txt
How to download the weights? (In this project: already downloaded)
!wget https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5s.pt
How to train the model?
Train the model on images with image size 416, batch size 8 and epochs 400: !python train.py --img 416 --batch 8 --epochs 400 --data data/data.yaml --weights yolov5s.pt --nosave --cache
How to predict using the model?
Predict on images with image size 640: !python detect.py --source data/dataset/predict/chess.mp4 --weights runs/train/exp2/weights/last.pt --img 640 --save-txt --save-conf
Result 1

As expected, the model doesn't perform that well... Maybe try with other angles?

The model performs way better, but still make a lot of mistakes. This needs to be better. Yolov9??
Owner
- Login: sebastienjacquemart-AI
- Kind: user
- Repositories: 1
- Profile: https://github.com/sebastienjacquemart-AI
GitHub Events
Total
Last Year
Dependencies
- pytorch/pytorch 2.0.0-cuda11.7-cudnn8-runtime build
- gcr.io/google-appengine/python latest build
- Pillow >=9.4.0
- PyYAML >=5.3.1
- gitpython >=3.1.30
- matplotlib >=3.3
- numpy >=1.23.5
- opencv-python >=4.1.1
- pandas >=1.1.4
- psutil *
- requests >=2.23.0
- scipy >=1.4.1
- seaborn >=0.11.0
- setuptools >=65.5.1
- thop >=0.1.1
- torchvision >=0.9.0
- tqdm >=4.64.0
- ultralytics >=8.0.232
- wheel >=0.38.0
- Flask ==2.3.2
- gunicorn ==19.10.0
- pip ==23.3
- werkzeug >=3.0.1