Image Classification
PyTorch
Safetensors
timm
medical-imaging
retinal-imaging
fundus
ophthalmology
multi-label-classification
ensemble
Eval Results (legacy)
Instructions to use Mjolnirslams/retinal-disease-ensemble with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use Mjolnirslams/retinal-disease-ensemble with timm:
import timm model = timm.create_model("hf_hub:Mjolnirslams/retinal-disease-ensemble", pretrained=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "architecture": "retinal_dual_eye_ensemble", | |
| "backbones": [ | |
| "efficientnet_b4", | |
| "inception_resnet_v2" | |
| ], | |
| "num_classes": 8, | |
| "dropout": 0.5, | |
| "image_size": 448, | |
| "norm_means": [ | |
| [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| ], | |
| "norm_stds": [ | |
| [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| ], | |
| "labels": [ | |
| "N", | |
| "D", | |
| "G", | |
| "C", | |
| "A", | |
| "H", | |
| "M", | |
| "O" | |
| ], | |
| "label_names": { | |
| "N": "Normal", | |
| "D": "Diabetes", | |
| "G": "Glaucoma", | |
| "C": "Cataract", | |
| "A": "AMD", | |
| "H": "Hypertension", | |
| "M": "Myopia", | |
| "O": "Other" | |
| }, | |
| "thresholds": [ | |
| 0.45268115401268005, | |
| 0.5955283641815186, | |
| 0.7139220833778381, | |
| 0.7515495419502258, | |
| 0.5114160180091858, | |
| 0.3302590250968933, | |
| 0.540062427520752, | |
| 0.5132951736450195 | |
| ], | |
| "weights_file": "model.safetensors" | |
| } | |