https://github.com/dnouri/cuda-convnet

My fork of Alex Krizhevsky's cuda-convnet from 2013 where I added dropout, among other features.
https://github.com/dnouri/cuda-convnet

Last synced: 3 months ago
JSON representation

My fork of Alex Krizhevsky's cuda-convnet from 2013 where I added dropout, among other features.

• Host: GitHub
• URL: https://github.com/dnouri/cuda-convnet
• Owner: dnouri
• Created: 2013-06-08T21:19:06.000Z (about 11 years ago)
• Default Branch: master
• Last Pushed: 2015-01-23T20:38:44.000Z (over 9 years ago)
• Last Synced: 2024-01-18T10:59:33.549Z (5 months ago)
• Language: Cuda
• Homepage: http://code.google.com/p/cuda-convnet/
• Size: 1.12 MB
• Stars: 246
• Watchers: 30
• Forks: 147
• Open Issues: 7
• Metadata Files:
  • Readme: README.rst

Lists

• alex-mikhalev-awesome-stars - cuda-convnet - Fork of Alex Krizhevsky's cuda-convnet 1. Adds dropout. (Cuda)
• my-awesome-stars - dnouri/cuda-convnet - My fork of Alex Krizhevsky's cuda-convnet from 2013 where I added dropout, among other features. (Cuda)

README

        
This is my fork of the ``cuda-convnet`` convolutional neural network

implementation written by Alex Krizhevsky.

``cuda-convnet`` has quite extensive documentation itself.  Find the

`MAIN DOCUMENTATION HERE `_.

**Update**: A newer version, `cuda-convnet 2

`_, has been released by

Alex.  This fork is still based on the original cuda-convnet.

===================

Additional features

===================

This document will only describe the small differences between

``cuda-convnet`` as hosted on Google Code and this version.

Dropout

=======

Dropout is a relatively new regularization technique for neural

networks.  See the `Improving neural networks by preventing

co-adaptation of feature detectors `_

and `Improving Neural Networks with Dropout

`_ papers for

details.

To set a dropout rate for one of our layers, we use the ``dropout``

parameter in our model's ``layer-params`` configuration file.  For

example, we could use dropout for the last layer in the CIFAR example

by modifying the section for the fc10 layer to look like so::

  [fc10]

  epsW=0.001

  epsB=0.002

  # ...

  dropout=0.5

In practice, you'll probably also want to double the number of

``outputs`` in that layer.

CURAND random seeding

=====================

An environment variable ``CONVNET_RANDOM_SEED``, if set, will be used

to set the CURAND library's random seed.  This is important in order

to get reproducable results.

Updated to work with CUDA via CMake

===================================

The build configuration and code has been updated to work with CUDA

via CMake. Run ``cmake .`` and then ``make``. If you have an alternative

BLAS library just set it with for example ``cmake -DBLAS_LIBRARIES=/usr/lib/libcblas.so  .``.