Vistransformers Explained

RESOURCE

Abstract

The Vistransformers Explained library is a collection of python notebooks that demonstrate the internal mechanics and uses of visual-transformer (ViT) machine learning models. The code implements, with mild modifications, ViT models that have been made publicly available through publication and GitHub code. The value added by this code is in-depth explanations of the mathematics behind the sub-modules of the ViT models, including original figures. Additionally, the library contains the code necessary to implement and train the ViT models. The library does not include example training data for the models; instead, it would rely on users generating their own datasets. The code is based on the PyTorch python library. It does not include any files other than python scripts, modules, or notebooks.
Developers:
Release Date:
2024-01-24
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Licenses:
BSD 3-clause "New" or "Revised" License
Sponsoring Org.:
Code ID:
125432
Site Accession Number:
O4693
Research Org.:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

Callis, Skylar. Vistransformers Explained. Computer Software. https://github.com/lanl/vision_transformers_explained. USDOE National Nuclear Security Administration (NNSA). 24 Jan. 2024. Web. doi:10.11578/dc.20240322.8.
Callis, Skylar. (2024, January 24). Vistransformers Explained. [Computer software]. https://github.com/lanl/vision_transformers_explained. https://doi.org/10.11578/dc.20240322.8.
Callis, Skylar. "Vistransformers Explained." Computer software. January 24, 2024. https://github.com/lanl/vision_transformers_explained. https://doi.org/10.11578/dc.20240322.8.
@misc{ doecode_125432,
title = {Vistransformers Explained},
author = {Callis, Skylar},
abstractNote = {The Vistransformers Explained library is a collection of python notebooks that demonstrate the internal mechanics and uses of visual-transformer (ViT) machine learning models. The code implements, with mild modifications, ViT models that have been made publicly available through publication and GitHub code. The value added by this code is in-depth explanations of the mathematics behind the sub-modules of the ViT models, including original figures. Additionally, the library contains the code necessary to implement and train the ViT models. The library does not include example training data for the models; instead, it would rely on users generating their own datasets. The code is based on the PyTorch python library. It does not include any files other than python scripts, modules, or notebooks.},
doi = {10.11578/dc.20240322.8},
url = {https://doi.org/10.11578/dc.20240322.8},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20240322.8}},
year = {2024},
month = {jan}
}