Santiago Castro's repositories
micromodels
Micromodels -- A framework for accurate, explainable, data efficient, and reusable NLP models.
AbnormalEventDetection
Abnormal Event Detection in Surveillance Systems
arxiv-latex-cleaner
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
blester125.github.io
My site hosted on github
conda-docs
Conda documentation
cudatoolkit-dev-feedstock
A conda-smithy repository for cudatoolkit-dev.
decord
An efficient video loader for deep learning with smart shuffling that's super easy to digest
ghpages
Deploy arbitrary static assets through GitHub Actions
jsonargparse
Parsing of command line options, yaml/jsonnet config files and/or environment variables based on argparse
lpips-feedstock
A conda-smithy repository for lpips.
Mask-Align
Code for our paper "Mask-Align: Self-Supervised Neural Word Alignment" in ACL 2021
MIL-NCE_HowTo100M
PyTorch GPU distributed training code for MIL-NCE HowTo100M
PerceptualSimilarity
LPIPS metric. pip install lpips
pytest
The pytest framework makes it easy to write small tests, yet scales to support complex functional testing
Ranger-Deep-Learning-Optimizer
Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase
tarp
Fast and simple stream processing of files in tar files, useful for deep learning, big data, and many other applications.
transformers
👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)