anna - GitLite

KO | EN

gitlite — search

#python #react #typescript #go #rust #docker #macos #java #windows #vue #awesome-list #pytorch #ios #open-source

anna

(★ 56)

This is a code repository to efficiently train a deconvolutional neural network with rectified linear units.

File Explorer

Download Latest Version (.zip)

- - __init__.py
  - supervised_data_loader.py
  - supervised_dataset.py
  - unsupervised_data_loader.py
  - unsupervised_dataset.py
- - .gitkeep
  - __init__.py
  - cc_layers.py
  - layers.py
  - LICENSE
- - __init__.py
- - launcher.py
  - log_plot_all.py
  - log_plotter.py
  - zeiler_plotter.py
- - .gitkeep
- - .gitkeep
  - __init__.py
- __init__.py
- anna.png
- - creating_new_dataset.md
  - creating_new_layer.md
  - creating_new_model_type.md
  - creating_new_util.md
  - developer_guidlines.md
  - getting_started.md
  - index.md
  - installation.md
  - utils_list.md
- - index.html
- mkdocs.yml
.gitignore
LICENSE
README.md
TODO.md

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

![Anna](https://raw.githubusercontent.com/ifp-uiuc/anna/master/assests/anna.png)
Artifical neural networks, anytime 
================

This is a code repository to efficiently train a deconvolutional neural network with rectified linear units.

This code uses [theano][theano], [pylearn2][pylearn2], [cuda-convnet][ccnet] and is heavily based on Sander Dieleman's [kaggle galaxy repo][galaxy].

It also currently relies on a change to `pylearn2.sandbox.cuda_convnet.pool.py` that defines a `grad` method for the `MaxPoolGrad` class, which can be useful in some cases...

## ICLR 2015 Paper Repo
If you came here via our paper [An Analysis of Unsupervised Pre-training in Light of Recent Advances][paper_arxiv_link], please go [here][paper_repo] to access the experiments we ran.

## Layout of the code
There are currently 3 main modules:
+ datasets - generic dataset classes
+ layers - layer definitions
+ util - utilities for training, evaluating, and saving/loading checkpoints

[theano]:https://github.com/Theano/Theano
[pylearn2]:https://github.com/lisa-lab/pylearn2
[ccnet]:http://code.google.com/p/cuda-convnet/
[galaxy]:https://github.com/benanne/kaggle-galaxies
[paper_arxiv_link]:http://arxiv.org/abs/1412.6597
[paper_repo]:https://github.com/ifp-uiuc/an-analysis-of-unsupervised-pre-training-iclr-2015