Clarify FAHR-FaceSurvival weight availability
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ Checkpoints for FAHR-Face and FAHR-FaceAge, accompanying our *Lancet Digital Hea
|
|
| 21 |
|
| 22 |
FAHR-Face is a ViT masked autoencoder pretrained on more than 40 million WebFace42M photographs. FAHR-FaceAge was fine-tuned on 743,152 photographs from ten public datasets and achieved a mean absolute error of 5.1 years on APPA-REAL (6,783 photographs). See the paper for methods and clinical evaluation.
|
| 23 |
|
| 24 |
-
FAHR-FaceSurvival weights are not
|
| 25 |
|
| 26 |
## Prepare images first
|
| 27 |
|
|
|
|
| 21 |
|
| 22 |
FAHR-Face is a ViT masked autoencoder pretrained on more than 40 million WebFace42M photographs. FAHR-FaceAge was fine-tuned on 743,152 photographs from ten public datasets and achieved a mean absolute error of 5.1 years on APPA-REAL (6,783 photographs). See the paper for methods and clinical evaluation.
|
| 23 |
|
| 24 |
+
FAHR-FaceSurvival weights are not publicly released. Both released files are PyTorch checkpoints containing `model_state_dict` and optimizer state.
|
| 25 |
|
| 26 |
## Prepare images first
|
| 27 |
|