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
File size: 668 Bytes
3c76023 | 1 2 3 4 5 6 7 8 9 10 | This repository's encoders at stage 2 and later were trained by distillation from H-optimus-0 (Bioptimus), which is
released under the Apache License, Version 2.0: https://www.apache.org/licenses/LICENSE-2.0
H-optimus-0 itself is not redistributed here. Our encoders are new weights (a ViT-S/16, 22M parameters) trained to match
its outputs on TCGA tiles.
Training and evaluation data: The Cancer Genome Atlas (NCI Genomic Data Commons, open access); CPTAC-BRCA (open);
Yale-HER2 (The Cancer Imaging Archive, HER2-TUMOR-ROIS, CC BY 4.0). HEROHE (CC BY-NC-ND 3.0) and BCNB (non-commercial)
were used for evaluation only, and no per-slide data from them are included.
|