Cat Reid Dinov3

--- license: mit tags: - re-identification - metric-learning - cat - dinov3 - pytorch pipeline_tag: image-feature-extraction --- # Cat ReID — DINOv3 Fine-tuned Fine-tuned [DINOv3 ViT-B/16](https://huggingface.co/timm/vit_base_patch16_dinov3.lvd1689m) for cat re-identification. ## Usage ```python import torch from ai.feature_extractor import VisionFeatureExtractor extractor = VisionFeatureExtractor(device="cpu", checkpoint="finetuned_best.pt") feature = extractor.extract(image) # 256-dim normalized embedding ``` ## Model - **Backbone**: DINOv3 ViT-B/16 (768-dim) - **Head**: Linear(768 → 256) + L2-norm - **Training**: Triplet margin loss with batch-hard mining - **Classes**: 131 cats