Metadata-Version: 2.1
Name: mozuma
Version: 0.0.dev0
Summary: Model Zoo for Multimedia Applications
Home-page: https://github.com/mozuma/mozuma
Author: Distributed Information Systems Laboratory, EPFL
Maintainer: Massonnet Stéphane
Maintainer-email: stephane.massonnet@epfl.ch
License: MIT License
Project-URL: Bug Tracker, https://github.com/mozuma/mozuma/issues
Keywords: vision and language,multimedia search
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: GPU :: NVIDIA CUDA :: 11.1
Classifier: Environment :: GPU :: NVIDIA CUDA :: 11.3
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Multimedia
Classifier: Topic :: Multimedia :: Video
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Classifier: Topic :: Scientific/Engineering :: Visualization
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: boto3
Requires-Dist: click
Requires-Dist: requests
Requires-Dist: scipy
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: opencv-python-headless
Requires-Dist: tqdm
Requires-Dist: pytorch-ignite
Requires-Dist: dill
Requires-Dist: yacs
Requires-Dist: ftfy
Requires-Dist: regex
Requires-Dist: mozuma-clip
Requires-Dist: facenet-pytorch
Requires-Dist: tokenizers
Requires-Dist: scikit-learn

# MoZuMa

MoZuMa is a library containing a collection of machine learning models
with standardised interface to run inference, train and manage model state files.

It aims at providing high-level abstractions called [runners](references/runners.md)
on top of inference and training loops
while allowing extensions via [callbacks](references/callbacks.md).
These callbacks control the way the output of a runner is handled
(i.e. features, labels, model weights...).

We also try to keep as few dependencies as possible.
Meaning models will be mostly implemented from
modules available in deep learning frameworks (such as `PyTorch` or `torchvision`).

See the  for more information.

## Quick links

- [Documentation](https://mozuma.github.io/mozuma/)
- [Installation](https://mozuma.github.io/mozuma/0-installation)
- [Getting started](https://mozuma.github.io/mozuma/1-getting-starteg)
- [Models](https://mozuma.github.io/mozuma/models/)


## Example gallery

See `docs/examples/` for a collection of ready to use notebooks.
