Image Feature Extraction
timm
PyTorch
Safetensors
red-blood-cells
hematology
medical-imaging
vision-transformer
dino
dinov2
feature-extraction
foundation-model
Eval Results (legacy)
Instructions to use Snarcy/RedDino-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use Snarcy/RedDino-base with timm:
import timm model = timm.create_model("hf_hub:Snarcy/RedDino-base", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -74,7 +74,7 @@ Unlike general-purpose models pretrained on natural images, RedDino incorporates
|
|
| 74 |
|
| 75 |
## Model Details
|
| 76 |
|
| 77 |
-
- **Architecture:** ViT-base, patch size
|
| 78 |
- **SSL framework:** DINOv2 (customized for RBC morphology)
|
| 79 |
- **Pretraining dataset:** 1.25M RBC images from 18 datasets
|
| 80 |
- **Embedding size:** 768
|
|
|
|
| 74 |
|
| 75 |
## Model Details
|
| 76 |
|
| 77 |
+
- **Architecture:** ViT-base, patch size 14
|
| 78 |
- **SSL framework:** DINOv2 (customized for RBC morphology)
|
| 79 |
- **Pretraining dataset:** 1.25M RBC images from 18 datasets
|
| 80 |
- **Embedding size:** 768
|