---
license: cc-by-4.0
library_name: pytorch
---

A lymphocyte classification model. This model is an InceptionV4 (without batch normalization)
and was trained on 23 types of cancers from TCGA.

Please refer to the [original GitHub Repo](https://github.com/ShahiraAbousamra/til_classification) 
and the [associated paper](https://doi.org/10.3389/fonc.2021.806603). If you find this model useful,
please consider citing relevant paper:

```bibtex
@article{abousamra2022deep,
  title={Deep learning-based mapping of tumor infiltrating lymphocytes in whole slide images of 23 types of cancer},
  author={Abousamra, Shahira and Gupta, Rajarsi and Hou, Le and Batiste, Rebecca and Zhao, Tianhao and Shankar, Anand and Rao, Arvind and Chen, Chao and Samaras, Dimitris and Kurc, Tahsin and others},
  journal={Frontiers in oncology},
  volume={11},
  pages={5971},
  year={2022},
  publisher={Frontiers}
}
```

The model was converted from its original TF Slim implementation to PyTorch using the script
`convert_tf_to_pytorch_til_inceptionv4.py` (in this repository).