Image Classification
timm
English
medical-imaging
knee-mri
acl-tear-detection
deep-learning
convnext
self-attention
masked-slice-modeling
radiology
orthopedics
Eval Results (legacy)
Instructions to use shareefch1413/ACL-LKNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use shareefch1413/ACL-LKNet with timm:
import timm model = timm.create_model("hf-hub:shareefch1413/ACL-LKNet", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Download src/__init__.py from shareefch1413/ACL-LKNet: direct link, hf CLI and curl.
- Browser
- Download file 903 Bytes
-
https://huggingface.co/shareefch1413/ACL-LKNet/resolve/main/src/__init__.py
- Command line
-
hf download hf://shareefch1413/ACL-LKNet/src/__init__.py
-
curl -L -o __init__.py https://huggingface.co/shareefch1413/ACL-LKNet/resolve/main/src/__init__.py
903 Bytes
| # ACL-LKNet: Anatomically Aware Self-Supervised Large-Kernel Network | |
| # for ACL Tear Detection in Knee MRI | |
| from .config import Config | |
| from .dataset import MRNetDataset, MRNetSSLDataset, create_dataloaders, get_stratified_folds | |
| from .evaluate import ( | |
| compute_metrics, | |
| compute_metrics_with_ci, | |
| find_optimal_thresholds, | |
| generate_threshold_sweep, | |
| plot_threshold_curves, | |
| plot_confusion_matrices_dual, | |
| evaluate_slice_explainability, | |
| evaluate_perturbation_faithfulness, | |
| evaluate_slice_localization, | |
| evaluate_msm_reconstruction, | |
| evaluate_scanner_perturbation_robustness, | |
| delong_test, | |
| mcnemar_test, | |
| full_evaluation, | |
| ) | |
| try: | |
| from .models.acl_lknet import ACLLKNet, create_model_from_config | |
| from .models.msm import MaskedSliceModeling | |
| from .train import train_supervised, pretrain_msm, train_5fold_cross_validation | |
| except ImportError: | |
| pass | |