Update README.md
Browse files
README.md
CHANGED
|
@@ -24,10 +24,16 @@ To learn more about how to use the model, we encourage you to read our blog post
|
|
| 24 |
|
| 25 |
- **Developed by:** Owkin
|
| 26 |
- **Funded by:** Owkin and IDRIS
|
| 27 |
-
- **Model type:** Vision Transformer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
- **License:** [Owkin non-commercial license](https://github.com/owkin/HistoSSLscaling/blob/main/LICENSE.txt)
|
| 29 |
-
|
| 30 |
-
|
| 31 |
## Uses
|
| 32 |
|
| 33 |
### Direct Use
|
|
|
|
| 24 |
|
| 25 |
- **Developed by:** Owkin
|
| 26 |
- **Funded by:** Owkin and IDRIS
|
| 27 |
+
- **Model type:** Vision Transformer Base
|
| 28 |
+
- **Model Stats:**
|
| 29 |
+
- Params (M): 85.8
|
| 30 |
+
- Image size: 224 x 224 x 3
|
| 31 |
+
- **Paper:**
|
| 32 |
+
- Scaling Self-Supervised Learning for Histopathology with Masked Image Modeling. A. Filiot et al., medRxiv 2023.07.21.23292757; doi: [https://doi.org/10.1101/2023.07.21.23292757](https://www.medrxiv.org/content/10.1101/2023.07.21.23292757v2)
|
| 33 |
+
- **Pretrain Dataset:** 40 million pan-cancer tiles extracted from [TGCA](https://portal.gdc.cancer.gov/)
|
| 34 |
+
- **Original:** https://github.com/owkin/HistoSSLscaling/
|
| 35 |
- **License:** [Owkin non-commercial license](https://github.com/owkin/HistoSSLscaling/blob/main/LICENSE.txt)
|
| 36 |
+
|
|
|
|
| 37 |
## Uses
|
| 38 |
|
| 39 |
### Direct Use
|