Metadata-Version: 2.1
Name: torchbearer-variational
Version: 0.1.0
Summary: A variational auto-encoder library for PyTorch using torchbearer
Home-page: https://github.com/pytorchbearer/variational
Author: Ethan Harris
Author-email: ewah1g13@ecs.soton.ac.uk
License: MIT
Download-URL: https://github.com/pytorchbearer/variational/archive/0.1.0.tar.gz
Description: # \[WIP\] torchbearer.variational
        A Variational Auto-Encoder library for PyTorch with torchbearer
        
        ## Contents
        - [About](#about)
        - [Installation](#installation)
        - [Goals](#goals)
        
        <a name="about"/>
        
        ## About
        
        Torchbearer.variational is a companion package to [torchbearer](https://github.com/ecs-vlc/torchbearer) which is intended to
        re-implement state of the art models and practices relating to the world of Variational Auto-Encoders (VAEs). The goal
        is to provide everything from useful abstractions to complete re-implementations of papers. This is in order to support
        both research and teaching / learning regarding VAEs.
        
        <a name="installation"/>
        
        ## Installation
        
        TBC
        
        <a name="goals"/>
        
        ## Goals
        
        Currently, _variational_ only includes abstractions for simple VAEs and some accompaniments, the next steps are as follows:
        
        - Construct some separate part of the docs for the _variational_ content
        - Implement a series of standard models with associated notes pages and example usages
        - Implement other divergences not in PyTorch such as MMD, Jensen-Shannon, etc.
        - Implement and document tools for sampling the latent spaces of models and producing figures
        - Implement other dataloaders not in torchvision and add associated docs
Platform: UNKNOWN
Requires-Python: >=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*
Description-Content-Type: text/markdown
