Image Classification
Transformers
Tibetan
dinov3
tibetan
script-classification
paleography
fine-tuned
document-analysis
Eval Results (legacy)
Instructions to use openpecha/tibetan-script-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openpecha/tibetan-script-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="openpecha/tibetan-script-classifier") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openpecha/tibetan-script-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "experiment": "patches_clahe", | |
| "data_dir": "./Data/output/patches_clahe", | |
| "exclude_manifest": "./benchmark_page_ids.json", | |
| "num_classes": 18, | |
| "checkpoint_results": { | |
| "best_stage_a_head_only.pt": { | |
| "patch_metrics": { | |
| "loss": 1.252472641594146, | |
| "accuracy": 0.5506856023506367, | |
| "macro_f1": 0.47513258745169057, | |
| "weighted_f1": 0.5599438485560059 | |
| }, | |
| "page_metrics": { | |
| "accuracy": 0.5793838862559242, | |
| "macro_f1": 0.48727754394876716, | |
| "weighted_f1": 0.5878127224538057, | |
| "num_pages": 844, | |
| "num_samples": 4084 | |
| }, | |
| "val_macro_f1_at_save": 0.5136114729148367, | |
| "epoch_at_save": 18 | |
| }, | |
| "best_stage_b_last_2_blocks.pt": { | |
| "patch_metrics": { | |
| "loss": 1.2555613597156252, | |
| "accuracy": 0.5614593535749265, | |
| "macro_f1": 0.49372885021461854, | |
| "weighted_f1": 0.5659541837806491 | |
| }, | |
| "page_metrics": { | |
| "accuracy": 0.5995260663507109, | |
| "macro_f1": 0.5293513765903048, | |
| "weighted_f1": 0.6026293588445379, | |
| "num_pages": 844, | |
| "num_samples": 4084 | |
| }, | |
| "val_macro_f1_at_save": 0.5008343237274931, | |
| "epoch_at_save": 7 | |
| }, | |
| "best_stage_c_last_4_blocks.pt": { | |
| "patch_metrics": { | |
| "loss": 1.2517013753546324, | |
| "accuracy": 0.5631733594515181, | |
| "macro_f1": 0.49105727133084387, | |
| "weighted_f1": 0.5689654809805166 | |
| }, | |
| "page_metrics": { | |
| "accuracy": 0.5995260663507109, | |
| "macro_f1": 0.5260995491182711, | |
| "weighted_f1": 0.6006737611724785, | |
| "num_pages": 844, | |
| "num_samples": 4084 | |
| }, | |
| "val_macro_f1_at_save": 0.5169021957485435, | |
| "epoch_at_save": 5 | |
| }, | |
| "final_model.pt": { | |
| "patch_metrics": { | |
| "loss": 1.2517013753546324, | |
| "accuracy": 0.5631733594515181, | |
| "macro_f1": 0.49105727133084387, | |
| "weighted_f1": 0.5689654809805166 | |
| }, | |
| "page_metrics": { | |
| "accuracy": 0.5995260663507109, | |
| "macro_f1": 0.5260995491182711, | |
| "weighted_f1": 0.6006737611724785, | |
| "num_pages": 844, | |
| "num_samples": 4084 | |
| }, | |
| "val_macro_f1_at_save": -1.0, | |
| "epoch_at_save": null | |
| } | |
| } | |
| } |