|
Download README.md from sneo/v802-classifier: direct link, hf CLI and curl.
- Browser
- Download file 2.38 kB
-
https://huggingface.co/sneo/v802-classifier/resolve/main/README.md
- Command line
-
hf download hf://sneo/v802-classifier/README.md
-
curl -L -o README.md https://huggingface.co/sneo/v802-classifier/resolve/main/README.md
2.38 kB
| library_name: scikit-learn | |
| pipeline_tag: image-classification | |
| tags: | |
| - multi-label | |
| - dinov3 | |
| # v802 classifier | |
| Multi-label image classifier that predicts which of six characters appear in an image: | |
| Applejack, Fluttershy, Pinkie Pie, Rainbow Dash, Rarity, Twilight Sparkle. | |
| - Backbone (frozen, **not included**): DINOv3 ViT-L/16, `facebook/dinov3-vitl16-pretrain-lvd1689m` | |
| - Head (`assets/v802/classifier.joblib`): ensemble of a MIL head on patch tokens from layers 16/20/24 (weight 0.6) | |
| and a per-class logistic-regression probe (weight 0.4), followed by a label-set decoder with a label-set prior and | |
| a cardinality model. The output is a set of labels plus per-class probabilities. | |
| - Input: RGB resized to 640x352, inferred on the original and its horizontal flip. Runs on CPU. | |
| ## Files | |
| | Path | Contents | | |
| |---|---| | |
| | `assets/v802/classifier.joblib` | Trained head bundle (`classes`, `components`, `config`, `decoder`) | | |
| | `src/` | Inference, training and experiment code | | |
| | `requirements.txt` | Pinned dependency versions used in production | | |
| `classifier.joblib` is a pickle. Loading it executes code, so only load it from a source you trust. | |
| ## Setup | |
| 1. Request access to `facebook/dinov3-vitl16-pretrain-lvd1689m` on Hugging Face (gated under the DINOv3 license), | |
| then download it: | |
| ```bash | |
| hf download facebook/dinov3-vitl16-pretrain-lvd1689m --local-dir models/dinov3-vitl16 | |
| ``` | |
| 2. Install dependencies (torch is the CPU build): | |
| ```bash | |
| pip install --extra-index-url https://download.pytorch.org/whl/cpu -r requirements.txt | |
| ``` | |
| ## Inference | |
| ```bash | |
| python src/predict_v802.py \ | |
| --bundle assets/v802/classifier.joblib \ | |
| --model models/dinov3-vitl16 \ | |
| image1.jpg images_dir/ | |
| ``` | |
| Options: `--threads N` (default 4), `--fp32` (disable bf16 autocast), `--output out.jsonl`. | |
| Each line of output is JSON: `{"file": ..., "labels": [...], "probabilities": {class: p, ...}}`. | |
| `src/serve_v802.py` takes the same `--bundle` / `--model` arguments and serves a minimal HTTP endpoint (`--port`, default 8802). | |
| ## Notes | |
| - Training and experiment scripts (`train_*`, `experiment_*`, `extract_features_*`, `build_v802.py`) expect an | |
| `artifacts/` tree of datasets, splits and features that is not included, so they will not run as-is. | |
| - Training data: 736 labeled dev images plus two 32-image holdout sets (not included). | |