Image Feature Extraction
timm
Safetensors
pathology
histopathology
her2
breast-cancer
h-and-e
vision-transformer
multiple-instance-learning
Instructions to use cloudkites/her2-reader with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use cloudkites/her2-reader with timm:
import timm model = timm.create_model("hf-hub:cloudkites/her2-reader", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Download data/paper/paper-data/table_rank.tex from cloudkites/her2-reader: direct link, hf CLI and curl.
- Browser
- Download file 1.04 kB
-
https://huggingface.co/cloudkites/her2-reader/resolve/main/data/paper/paper-data/table_rank.tex
- Command line
-
hf download hf://cloudkites/her2-reader/data/paper/paper-data/table_rank.tex
-
curl -L -o table_rank.tex https://huggingface.co/cloudkites/her2-reader/resolve/main/data/paper/paper-data/table_rank.tex
1.04 kB
| % Generated by docs/paper/paper_data.py (ten-seed means; superscript: rank in the column) | |
| \begin{tabularx}{\linewidth}{@{}>{\raggedright\arraybackslash}X l r r cccc@{}} | |
| \toprule | |
| tile encoder & architecture & params & CPU s & Yale$\to$Yale & TCGA$\to$TCGA & TCGA$\to$Yale & Yale$\to$TCGA \\ | |
| \midrule | |
| \textbf{Ours (final)} & ViT-S/16 & 22M & 8.4 & \textbf{0.844$^{3}$} & \textbf{0.690$^{1}$} & \textbf{0.812$^{1}$} & \textbf{0.650$^{3}$} \\ | |
| Phikon & ViT-B/16 & 86M & 23.0 & 0.872$^{2}$ & 0.679$^{2}$ & 0.811$^{2}$ & 0.662$^{1}$ \\ | |
| H-optimus-0 & ViT-g/14 & 1.1B & 312 & 0.897$^{1}$ & 0.676$^{3}$ & 0.805$^{3}$ & 0.653$^{2}$ \\ | |
| Hibou-B & ViT-B/14 & 86M & -- & 0.786$^{5}$ & 0.626$^{4}$ & 0.749$^{4}$ & 0.637$^{5}$ \\ | |
| Midnight-12k & ViT-g/14 & 1.1B & 312$^\dagger$ & 0.834$^{4}$ & 0.623$^{5}$ & 0.727$^{5}$ & 0.638$^{4}$ \\ | |
| ResNet-50$^\ast$ & CNN & 26M & -- & 0.700$^{6}$ & 0.545$^{6}$ & 0.638$^{6}$ & 0.568$^{7}$ \\ | |
| DINOv2-S$^\ast$ & ViT-S/14 & 22M & -- & 0.676$^{7}$ & 0.495$^{7}$ & 0.589$^{7}$ & 0.573$^{6}$ \\ | |
| \bottomrule | |
| \end{tabularx} | |