Tibetan Page Orientation Classifier
Predict whether a tibetan manuscript page image is upright (nonflipped) or upside-down (flipped, 180°).
Source du modèle
- Type
- Other
- Taille du fichier
- 82,7 MB
- Modèle de base
- facebook/dinov3-vits16-pretrain-lvd1689m
- Version
- vRevision 12ef840
- Mis à jour
- 17 sept. 2026
- Téléchargements
- 25
- Source
- Hugging Face
Description de la source
Tibetan page orientation classifier (DINOv3 ViT-S)
Predict whether a tibetan manuscript page image is upright (non_flipped) or upside-down (flipped, 180°).
Fine-tuned DINOv3 ViT-S.
Dataset (HF): BDRC/tibetan-page-orientation-classifier-dataset
Experiment: dinov3_binary_flip_center_cropped
Checkpoint: final_model.pt (best validation macro-F1 across stages A + B + C)
Preprocessing (inference)
| Split | Mode |
|---|---|
| train | center_crop |
| val | center_crop |
| test | center_crop |
Use the same mode as training before the DINO image processor (size 448).
Test metrics (n=854)
| Metric | Value |
|---|---|
| Accuracy | 100.0% |
| Macro F1 | 1.000 |
| AUC-ROC | 1.000 |
| Loss | 0.1237 |
Training config
| Setting | Value |
|---|---|
| Stages | A + B + C |
| Epochs A / B | 5 / 10 |
| LR head A | 0.0005 |
| LR backbone B | 5e-06 |
| LR head B | 5e-05 |
| Unfreeze blocks B | 4 |
| Scheduler | cosine_warmup |
| Class weights | none |
| Label smoothing | 0.05 |
Training history
Training curves
Per-epoch metrics: training_history.json and results.json → history.
Files
| File | Description |
|---|---|
final_model.pt | Weights + idx_to_label + test metrics |
results.json | Full training config, history, report |
training_history.json | Stage A/B epoch logs |
confusion_matrix.json | Machine-readable CM |
confusion_matrix.png | Plot |
training_history.png | Loss / F1 curves |
model_card.json | Summary metadata |
config.yaml | Training hyperparameters (copy) |
inference_classifier.py | CLI inference on image paths |
Load weights
import torch
ckpt = torch.load("final_model.pt", map_location="cpu", weights_only=False)
print(ckpt["test_metrics"])
print(ckpt["idx_to_label"])
Inference
Use the same preprocessing as training (center_crop, size 448). The bundled script reads defaults from model_card.json when flags are omitted.
pip install -r requirements-inference.txt
python inference_classifier.py --checkpoint final_model.pt --image page.jpg
Explicit flags (recommended for reproducibility):
python inference_classifier.py \
--checkpoint final_model.pt \
--image page.jpg \
--preprocess center_crop \
--preprocess-size 448
Classes: non_flipped = upright page; flipped = upside-down (180° rotation).
Citation
@misc{bdrcpageorientationmodel,
title = {Tibetan Page Orientation Classifier (DINOv3)},
author = {Buddhist Digital Resource Center and OpenPecha},
year = {2026},
url = {https://huggingface.co/BDRC/tibetan-page-orieantation-classifier},
dataset = {https://hunggingface.co/BDRC/tibetan-page-orientation-classifier-dataset},
experiment = {center-cropped}
note = {Trained on BDRC manuscript images}
}
License
Model weights and inference code: Apache License 2.0.
Acknowledgements
All images are provided by the Buddhist Digital Resource Center (BDRC). This dataset was developed by Dharmaduta from specifications provided by BDRC for the project "The BDRC Etext Corpus", with funding from the Khyentse Foundation. Buddhist Digital Resource Center (BDRC). Developed by Dharmaduta / OpenPecha.
Sources
1 source
Sources
1 sourceVérifié 2 sept.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactExtraits de sources
2 extraits
Extraits de sources
2 extraits--- language: - bo tags: - image-classification - tibetan - page-orientation - dinov3 library_name: transformers pipeline_tag: image-classification base_model: facebook/dinov3-vits16-pretrain-lvd1689m datasets: - BDRC/tibetan-page-orientation-classifier-dataset metrics: - f1 - accuracy - auc license: apache-2.0 --- # Tibetan page orientation classifier (DINOv3 ViT-S) Predict whether a tibetan manuscript page image is **upright** (`non_flipped`) or **upside-down** (`flipped`, 180°). Fine-tuned [DINOv3 ViT-S](https://huggingface.co/facebook/dinov3-vits16-pretrain-lvd1689m). **Dataset (HF):** [BDRC/tibetan-page-orientation-classifier-dataset](https://huggingface.co/datasets/BDRC/tibetan-page-orientation-classifier-dataset) **Experiment:** `dinov3_binary_flip_center_cropped` **Checkpoint:** `final_model.pt` (best validation macro-F1 across stages A + B + C) ## Preprocessing (inference) | Split | Mode | |-------|------| | train | `center_crop` | | val | `center_crop` | | test | `center_crop` | Use the same mode as training before the DINO image processor (size `448`). ## Test metrics (n=854) | Metric | Value | |--------|------:| | Accuracy | 100.0% | | Macro F1 | 1.000 | | AUC-ROC | 1.000 | | Loss | 0.1237 | ## Training config | Setting | Value | |---------|-------| | Stages | A + B + C | | Epochs A / B | 5 / 10 | | LR head A | 0.0005 | | LR backbone B | 5e-06 | | LR head B | 5e-05 | | Unfreeze blocks B | 4 | | Scheduler | `cosine_warmup` | | Class weights | `none` | | Label smoothing | 0.05 | ## Training history  Per-epoch metrics: `training_history.json` and `results.json` → `history`. ## Files | File | Description | |------|-------------| | `final_model.pt` | Weights + `idx_to_label` + test metrics | | `results.json` | Full training config, history, report | | `training_history.json` | Stage A/B epoch logs | | `confusion_matrix.json` | Machine-readable CM | | `confusion_matrix.png` | Plot | | `training_history.png` | Loss / F1 curves | | `model_card.json` | Summary metadata | | `config.yaml` | Training hyperparameters (copy) | | `inference_classifier.py` | CLI inference on image paths | ## Load weights ```python import torch ckpt = torch.load("final_model.pt", map_location="cpu", weights_only=False) print(ckpt["test_metrics"]) print(ckpt["idx_to_label"]) ``` ## Inference Use the same preprocessing...
Source context: 25 downloads · 0 likes · Pipeline image-classification · Library transformers · Repo BDRC/tibetan-page-orientation-classifier
