Model Zoo for Multimedia Applications
Project description
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 on top of inference and training loops while allowing extensions via callbacks. 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
Example gallery
See docs/examples/ for a collection of ready to use notebooks.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
