Snarcy
/

RedDino-base

Image Feature Extraction

red-blood-cells

medical-imaging

vision-transformer

feature-extraction

foundation-model

Model card Files Files and versions

Snarcy commited on Aug 12

Commit

2acd8f9

·

verified ·

1 Parent(s): 7687627

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -74,7 +74,7 @@ Unlike general-purpose models pretrained on natural images, RedDino incorporates
 ## Model Details
-- **Architecture:** ViT-base, patch size 16 (`b16`)
 - **SSL framework:** DINOv2 (customized for RBC morphology)
 - **Pretraining dataset:** 1.25M RBC images from 18 datasets
 - **Embedding size:** 768

 ## Model Details
+- **Architecture:** ViT-base, patch size 14
 - **SSL framework:** DINOv2 (customized for RBC morphology)
 - **Pretraining dataset:** 1.25M RBC images from 18 datasets
 - **Embedding size:** 768