Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Vistransformers Explained

Software ·
DOI:https://doi.org/10.11578/dc.20240322.8· OSTI ID:code-125432 · Code ID:125432

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.

Site Accession Number:
O4693
Software Type:
Scientific
License(s):
BSD 3-clause "New" or "Revised" License
Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)

Primary Award/Contract Number:
AC52-06NA25396
DOE Contract Number:
AC52-06NA25396
Code ID:
125432
OSTI ID:
code-125432
Country of Origin:
United States

Similar Records

Hyperparameter Studies for Vision Transformers Trained on High-Fidelity Simulations
Software · Tue May 28 20:00:00 EDT 2024 · OSTI ID:code-134596

PyTorch Implementation of Log-Additive Convolutional Neural Networks
Software · Wed May 15 20:00:00 EDT 2024 · OSTI ID:code-140120

labquake_future_prediction
Software · Wed Sep 14 20:00:00 EDT 2022 · OSTI ID:code-92609

Related Subjects