Commit 14e33b79 authored by Guillaume HEUSCH's avatar Guillaume HEUSCH

[doc] started updating the doc (WIP)

parent 4f892fdb
Pipeline #20094 failed with stage
in 99 minutes and 42 seconds
.. bob.learn.pytorch documentation master file, created by
sphinx-quickstart on Wed Nov 22 11:25:35 2017.
You can adapt this file completely to your liking, but it should at least
contain the root `toctree` directive.
====================
PyTorch Bob Bindings
====================
Welcome to bob.learn.pytorch's documentation!
=============================================
`bob.learn.pytorch` is a high-level library, written in Python that runs on top of PyTorch.
The goal here is to be able to do fast experimentation with neural networks.
This module contains the implementation of different Generative Adversarial Networks (GAN)
used for face processing (i.e. generating face images)
If you would like to have an idea on the basic principles of GAN, you should first read the
paper by Goodfellow et al.
https://arxiv.org/abs/1406.2661
This package makes heavy use of pytorch_, so make sure you have it installed on your environment. It also
relies on bob_ (and in particular for I/O and databases interfaces), so you may want to refer
to their respective documentation.
This package is basically organized as follows (some files are omitted for clarity purposes):
.. code-block:: text
bob/
+-- learn/
+-- pytorch/
+-- architectures/
+-- DCGAN.py
+-- ...
+-- datasets/
+-- multipie.py
+-- ...
+-- scripts/
+-- train_dcgan_multipie.py
+-- ...
+-- trainers/
+-- DCGANTrainer.py
+ ``architectures`` contains files defining the different discriminators and generators.
+ ``datasets`` contains files implementing the dataset as ``torch.utils.data.DataSet``, and some utility functions (wrapper around torch.transforms for instance)
+ ``scripts`` contains the various scripts to perform training.
+ ``trainers`` contains files implementing the different training procedure
===========
Users Guide
===========
.. toctree::
:maxdepth: 2
In order to build the package, activate your bob environment, and do::
user_guide.rst
$ buildout
In the user's guide you will find more detailed instructions on how to run the various examples.
================
Reference Manual
================
.. toctree::
:maxdepth: 3
:maxdepth: 2
guide_dcgan
guide_conditionalgan
guide_drgan
py_api
References
----------
.. [dcgan] *A.Radford, L. Metz, S. Chintala*. **Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks** Intl Conf. on Learning Representation, 2016. `arXiv <https://arxiv.org/abs/1511.06434>`__
.. [cgan] *M. Mirza, S. Osindero*. **Conditional Generative Adversarial Nets** `arXiv:1411.1784. <https://arxiv.org/abs/1411.1784>`__
Licensing
Licensing
---------
This work is licensed under the GPLv3_.
.. _GPLv3: http://www.gnu.org/licenses/gpl-3.0.en.html
.. _gridtk: https://pypi.python.org/pypi/gridtk
.. _bob: http://idiap.github.io/bob/
.. _pytorch: http://pytorch.org/
Indices and tables
------------------
......
py:class torch.nn.modules.module.Module
py:class torch.utils.data.dataset.Dataset
===========
User guide
===========
As the name suggest, this package makes heavy use of pytorch_, so make sure you have it installed on your environment.
It also relies on bob_ (and in particular for I/O and databases interfaces), so you may want to refer
to their respective documentation as well.
Anatomy of the package
----------------------
This package is basically organized as follows (some files are omitted for clarity purposes):
.. code-block:: text
bob/
+-- learn/
+-- pytorch/
+-- architectures/
+-- DCGAN.py
+-- ...
+-- datasets/
+-- multipie.py
+-- ...
+-- scripts/
+-- train_dcgan_multipie.py
+-- ...
+-- trainers/
+-- DCGANTrainer.py
+ ``architectures`` contains files defining the different discriminators and generators.
+ ``datasets`` contains files implementing the dataset as ``torch.utils.data.DataSet``, and some utility functions (wrapper around torch.transforms for instance)
+ ``scripts`` contains the various scripts to perform training.
+ ``trainers`` contains files implementing the different training procedure
.. _bob: http://idiap.github.io/bob/
.. _pytorch: http://pytorch.org/
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment