Instructions to use HaseLab/mahjong-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use HaseLab/mahjong-models with ultralytics:
from huggingface_hub import hf_hub_download from ultralytics import YOLO # pick the weights file from this repo's "Files and versions" tab weights = hf_hub_download("HaseLab/mahjong-models", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update ResNet-50 classifier after real-image fine-tuning
Verified signaturedb01725
-
Fix classifier labels and region classes
Verified signature400cd87 -
Update model documentation
Verified signature773d5e1 -
Add model usage documentation
Verified signature7f2a208 -
Keep three production model artifacts
Verified signature10afe37 -
Upload Mahjong recognition models
Verified signature3735654 -
initial commit
Verified signature15e5ce4