Metadata-Version: 2.1
Name: vltk
Version: 1.0.4
Summary: The Vision-Language Toolkit (VLTK)
Home-page: UNKNOWN
Author: Antonio Mendoza
Author-email: antonio36764@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Requires-Dist: appdirs
Requires-Dist: astroid
Requires-Dist: black
Requires-Dist: certifi
Requires-Dist: chardet
Requires-Dist: click
Requires-Dist: cycler
Requires-Dist: Cython
Requires-Dist: datasets (==1.9.0)
Requires-Dist: dill
Requires-Dist: einops
Requires-Dist: filelock
Requires-Dist: fire
Requires-Dist: flake8
Requires-Dist: GPUtil
Requires-Dist: idna
Requires-Dist: isort
Requires-Dist: joblib
Requires-Dist: jsonlines
Requires-Dist: kiwisolver
Requires-Dist: lazy-object-proxy
Requires-Dist: matplotlib
Requires-Dist: mccabe
Requires-Dist: multiprocess
Requires-Dist: numpy
Requires-Dist: opencv-python
Requires-Dist: packaging
Requires-Dist: pandas
Requires-Dist: pathspec
Requires-Dist: pep8
Requires-Dist: Pillow
Requires-Dist: pyaml
Requires-Dist: pyarrow
Requires-Dist: pycocotools
Requires-Dist: pycodestyle
Requires-Dist: pyflakes
Requires-Dist: pylint
Requires-Dist: pyparsing
Requires-Dist: python-dateutil
Requires-Dist: pytz
Requires-Dist: PyYAML
Requires-Dist: regex
Requires-Dist: requests
Requires-Dist: sacremoses
Requires-Dist: scipy
Requires-Dist: six
Requires-Dist: termcolor
Requires-Dist: timm
Requires-Dist: tokenizers
Requires-Dist: toml
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: tqdm
Requires-Dist: transformers (==4.8.2)
Requires-Dist: typed-ast
Requires-Dist: urllib3
Requires-Dist: wget
Requires-Dist: wrapt
Requires-Dist: xxhash
Requires-Dist: sphinx
Requires-Dist: sphinx-rtd-theme
Requires-Dist: recommonmark

# Installation
To install (add editable for personal custimization)
```
git clone https://github.com/eltoto1219/vltk.git && cd vltk && pip install -e .
```
Alternatively:
```
pip install vltk
```

# Documentation
The documentation is up! at [vltk documentation](http://avmendoza.info/vltk/)

It is pretty bare bones for now, however first on the agenda to be added will be:
1. Usage of adapters to rapidly create datasets.
2. An overview of all the config options for automatically instantiating PyTorch dataloaders from one to many different datasets at once
3. An overview of how dataset metadata is automatically + deterministically collected from multiple datasets 
4. Usage of modality prcoessors for language, vision, and language X vision which make it possible to universally load any visn, lang, visn-lang dataset. 


# Collaboration

There are many exciting directions and improvements I have in mind to make in vltk. While this is the  "official" beginning of the project, please email me for any suggestions/collaboration ideas: antonio36764@gmail.com 


