Image Classification
PyTorch
timm
multiple-instance-learning
attention
interpretability
digital-humanities
historical-documents
korean
Instructions to use aronvandepol/visual-feature-discovery with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use aronvandepol/visual-feature-discovery with timm:
import timm model = timm.create_model("hf-hub:aronvandepol/visual-feature-discovery", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Download eval/convnextv2_base_book_split_fold2.json from aronvandepol/visual-feature-discovery: direct link, hf CLI and curl.
- Browser
- Download file 716 Bytes
-
https://huggingface.co/aronvandepol/visual-feature-discovery/resolve/main/eval/convnextv2_base_book_split_fold2.json
- Command line
-
hf download hf://aronvandepol/visual-feature-discovery/eval/convnextv2_base_book_split_fold2.json
-
curl -L -o convnextv2_base_book_split_fold2.json https://huggingface.co/aronvandepol/visual-feature-discovery/resolve/main/eval/convnextv2_base_book_split_fold2.json
716 Bytes
| { | |
| "model_name": "convnextv2_base", | |
| "fold": 2, | |
| "n_folds": 5, | |
| "split_info": { | |
| "fold": 2, | |
| "train_samples": 44957, | |
| "val_samples": 8063, | |
| "test_samples": 13254, | |
| "train_books": 347, | |
| "val_books": 61, | |
| "test_books": 102, | |
| "train_val_overlap": 0, | |
| "train_test_overlap": 0, | |
| "val_test_overlap": 0 | |
| }, | |
| "test_results": { | |
| "test_loss_epoch": 0.5984542965888977, | |
| "test_accuracy": 0.8428398966789246, | |
| "test_precision": 0.83812016248703, | |
| "test_recall": 0.8699315190315247, | |
| "test_f1": 0.8505106568336487 | |
| }, | |
| "model_path": "models_book_split/convnextv2_base_fold2_20260203_1901.pth", | |
| "checkpoint_dir": "checkpoints_book_split/convnextv2_base_fold2_20260203_1901" | |
| } |