Skip to content

thijswerrij/Transformers-CBIS-DDSM

Repository files navigation

Classifying mammograms using visual transformers

Important files

  • pretrained_ResViT.py - Run a combination of a pretrained ResNet-18 model and visual transformer modules, based on Wu et al. [1], on CBIS-DDSM data [2].
  • resnet.py - Run a pretrained ResNet-18 model on CBIS-DDSM data [2].
  • cbis_ddsm_train.py - CBIS-DDSM data loading and helper functions (used by other files).
  • load_data.py - Cropping, downscaling and saving CBIS-DDSM data to hdf5 format. Necessary before running any experiments.

Acknowledgements

This repository uses code from two other repositories:

References

[1] Wu et al. (2020) Visual Transformers: Token-based Image Representation and Processing for Computer Vision https://arxiv.org/abs/2006.03677

[2] Rebecca Sawyer Lee et al. (2016). Curated Breast Imaging Subset of DDSM [Dataset]. The Cancer Imaging Archive. DOI: https://doi.org/10.7937/K9/TCIA.2016.7O02S9CY

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages