Instructions to use Aditya2162/ivus-segmentation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use Aditya2162/ivus-segmentation with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://Aditya2162/ivus-segmentation") - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model_dir": "models/multitask/lumen_multitask_base", | |
| "cls_head_path": "models/multitask/bifurcation_head.keras", | |
| "split_json": "evals/splits/ivus_split_merged_600.json", | |
| "num_test_samples": 90, | |
| "num_test_with_lumen": 48, | |
| "threshold_info": { | |
| "method": "validation_sweep", | |
| "metric": "cls_f1", | |
| "selected_threshold": 0.5199999999999999, | |
| "val_best": { | |
| "threshold": 0.5199999999999999, | |
| "cls_accuracy": 0.8888888888888888, | |
| "cls_precision": 0.8888888888888888, | |
| "cls_recall": 0.9491525423728814, | |
| "cls_f1": 0.9180327868852458, | |
| "cls_auc": 0.9111536741256714, | |
| "tp": 56, | |
| "fp": 7, | |
| "fn": 3, | |
| "tn": 24 | |
| } | |
| }, | |
| "segmentation_metrics": { | |
| "seg_count": 48, | |
| "seg_iou": 0.8519954307622618, | |
| "seg_dice": 0.920083728728844 | |
| }, | |
| "bifurcation_metrics": { | |
| "threshold": 0.5199999999999999, | |
| "cls_accuracy": 0.8555555555555555, | |
| "cls_precision": 0.9259259259259259, | |
| "cls_recall": 0.847457627118644, | |
| "cls_f1": 0.8849557522123893, | |
| "cls_auc": 0.9633679986000061, | |
| "tp": 50, | |
| "fp": 4, | |
| "fn": 9, | |
| "tn": 27 | |
| } | |
| } |