Instructions to use charuka0/acne-multilabel-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use charuka0/acne-multilabel-classifier with timm:
import timm model = timm.create_model("hf_hub:charuka0/acne-multilabel-classifier", pretrained=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "task": "multi-label acne type recognition", | |
| "classes": [ | |
| "Whitehead", | |
| "Blackhead", | |
| "Papule", | |
| "Pustule", | |
| "Nodule" | |
| ], | |
| "backbone": "efficientnet_b0", | |
| "img_size": 320, | |
| "normalization": { | |
| "mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ] | |
| }, | |
| "thresholds": [ | |
| 0.9300000000000002, | |
| 0.7200000000000002, | |
| 0.7500000000000002, | |
| 0.5000000000000001, | |
| 0.8200000000000002 | |
| ], | |
| "best_epoch": 20, | |
| "test_metrics": { | |
| "subset_accuracy": 0.9797979797979798, | |
| "label_accuracy": 0.9950937950937951, | |
| "hamming_loss": 0.004906204906204906, | |
| "macro_precision": 0.9920701754385967, | |
| "macro_recall": 0.9859189631845048, | |
| "macro_f1": 0.9889388150515815, | |
| "micro_precision": 0.9912790697674418, | |
| "micro_recall": 0.9841269841269841, | |
| "micro_f1": 0.9876900796524257, | |
| "macro_auc": 0.9992512177176863, | |
| "macro_ap": 0.9978351524589545 | |
| }, | |
| "n_train": 3231, | |
| "n_val": 693, | |
| "n_test": 693, | |
| "torch_version": "2.10.0+cu128", | |
| "timm_version": "1.0.26" | |
| } |