Mercurial > pylearn
view pylearn/formulas/noise.py @ 1301:1a3090eca2ec
make the noise type the same as the input.
author | Frederic Bastien <nouiz@nouiz.org> |
---|---|
date | Fri, 01 Oct 2010 14:42:34 -0400 |
parents | 24890ca1d96b |
children | 1b97fae7ea0d |
line wrap: on
line source
""" Noise functions used to train Denoising Auto-Associators. Functions in this module often include a `noise_lvl` argument that controls the amount of noise that the function applies. The noise contract is simple: noise_lvl is a symbolic variable going from 0 to 1. 0: no change. 1: maximum noise. """ import theano import tags s=""" * A latex mathematical description of the formulas(for picture representation in generated documentation) * Tags(for searching): * a list of lower lovel fct used * category(name of the submodule itself) * Tell if we did some work to make it more numerical stable. Do theano do the optimization needed? * Tell if the grad is numericaly stable? Do theano do the optimization needed? * Tell if work on gpu/not/unknow * Tell alternate name * Tell the domaine, range of the input/output(range should use the english notation of including or excluding) """ @tags.tags('noise','binomial','salt') def binomial_noise(theano_rng,input,noise_lvl): """ Return `inp` with randomly-chosen elements set to zero. TODO: MATH DEFINITION :type input: Theano tensor variable :param input: input :type noise_lvl: float :param noise_lvl: The probability of setting each element to zero. """ mask = theano_rng.binomial( size = inp.shape, n = 1, p = 1 - noise_lvl, dtype=inp.dtype) return mask * input @tags.tags('noise','binomial NLP','pepper','salt') def pepper_and_salt_noise(theano_rng,inp,noise_lvl): """ This add pepper and salt noise to inp :type inp: Theano variable :param inp: The input that we want to add noise :type noise_lvl: tuple(float,float) :param noise_lvl: The %% of noise for the salt and pepper. Between 0 (no noise) and 1. """ assert inp.dtype in ['float32','float64'] return theano_rng.binomial( size = inp.shape, n = 1, p = 1 - noise_lvl[0], dtype=inp.dtype) * inp \ + (inp==0) * theano_rng.binomial( size = inp.shape, n = 1, p = noise_lvl[1], dtype=inp.dtype) @tags.tags('noise','gauss','gaussian') def gaussian_noise(theano_rng,inp,noise_lvl): """ This add gaussian NLP noise to inp :type inp: Theano variable :param inp: The input that we want to add noise :type noise_lvl: float :param noise_lvl: The standard deviation of the gaussian. """ assert inp.dtype in ['float32','float64'] return theano_rng.normal( size = inp.shape, std = noise_lvl, dtype=inp.dtype) + inp