AIPython★ 2,798⑂ 228 forksApache-2.0
autodistill/autodistill
AUTODISTILL: TRAINING WITHOUT LABELING
Automatically turns raw images into ready-to-use inference models, using foundation models to generate pseudo‑labels and train supervised models. No manual labeling required.
// KEY FEATURES
- Generates pseudo‑labels for images using Grounding DINO and foundation models.
- Trains supervised models (YOLO, Detectron2) on pseudo‑labels without manual labeling.
- Exports models to ONNX, TorchScript, and TFLite for deployment.
- Incremental learning: add data and improve the model without new labeling.
#auto-labeling#computer-vision#deep-learning#foundation-models#grounding-dino#image-annotation#image-classification#instance-segmentation#labeling-tool#machine-learning#model-distillation#multimodal
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram