资源简介
这个存储库包含使用深度学习对高分辨率图像进行分解的工作的代码。目前最先进的方法,如BM3D,KSVD和非本地手段确实能够产生高质量的去噪效果。但是当图像的大小变得非常高时,例如。 4000 x 80000像素,那些高质量的结果以高计算时间为代价。这个耗时的因素可以作为一个动机来提出一个模型,可以在更短的时间内提供可比较的结果,如果不是更好的话。因此,我使用了一种深度学习方法,它会自动尝试学习将噪声图像映射到其去噪版本的功能。
代码片段和文件信息
from __future__ import print_function
import os
import sys
import timeit
import numpy
import theano
import theano.tensor as T
from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
from logistic_sgd import load_data
from utils import tile_raster_images
try:
import PIL.Image as Image
except ImportError:
import Image
class dA(object):
“““Denoising Auto-Encoder class (dA)
A denoising autoencoders tries to reconstruct the input from a corrupted
version of it by projecting it first in a latent space and reprojecting
it afterwards back in the input space. Please refer to Vincent et al.2008
for more details. If x is the input then equation (1) computes a partially
destroyed version of x by means of a stochastic mapping q_D. Equation (2)
computes the projection of the input into the latent space. Equation (3)
computes the reconstruction of the input while equation (4) computes the
reconstruction error.
.. math::
\tilde{x} ~ q_D(\tilde{x}|x) (1)
y = s(W \tilde{x} + b) (2)
x = s(W‘ y + b‘) (3)
L(xz) = -sum_{k=1}^d [x_k \log z_k + (1-x_k) \log( 1-z_k)] (4)
“““
def __init__(
self
numpy_rng
theano_rng=None
input=None
n_visible=784
n_hidden=500
W=None
bhid=None
bvis=None
):
“““
Initialize the dA class by specifying the number of visible units (the
dimension d of the input ) the number of hidden units ( the dimension
d‘ of the latent or hidden space ) and the corruption level. The
constructor also receives symbolic variables for the input weights and
bias. Such a symbolic variables are useful when for example the input
is the result of some computations or when weights are shared between
the dA and an MLP layer. When dealing with SdAs this always happens
the dA on layer 2 gets as input the output of the dA on layer 1
and the weights of the dA are used in the second stage of training
to construct an MLP.
:type numpy_rng: numpy.random.RandomState
:param numpy_rng: number random generator used to generate weights
:type theano_rng: theano.tensor.shared_randomstreams.RandomStreams
:param theano_rng: Theano random generator; if None is given one is
generated based on a seed drawn from ‘rng‘
:type input: theano.tensor.TensorType
:param input: a symbolic description of the input or None for
standalone dA
:type n_visible: int
:param n_visible: number of visible units
:type n_hidden: int
:param n_hidden: number of hidden units
:type W: theano.tensor.TensorType
:param W: Theano variable pointing to a set o
属性 大小 日期 时间 名称
----------- --------- ---------- ----- ----
目录 0 2017-12-14 10:45 image-denoising-master\
文件 2320 2017-12-14 10:45 image-denoising-master\README.md
文件 13234 2017-12-14 10:45 image-denoising-master\dA.py
目录 0 2017-12-14 10:45 image-denoising-master\data\
文件 86860 2017-12-14 10:45 image-denoising-master\data\band1_denoised1.png
文件 89019 2017-12-14 10:45 image-denoising-master\data\band1_denoised2.png
文件 96255 2017-12-14 10:45 image-denoising-master\data\band1_noisy1.png
文件 95355 2017-12-14 10:45 image-denoising-master\data\band1_noisy2.png
文件 29920 2017-12-14 10:45 image-denoising-master\denoise_function.py
目录 0 2017-12-14 10:45 image-denoising-master\graphs\
文件 20564 2017-12-14 10:45 image-denoising-master\graphs\patches_plot.png
文件 14858 2017-12-14 10:45 image-denoising-master\graphs\psnr_plot.png
文件 21213 2017-12-14 10:45 image-denoising-master\graphs\variation_with_no_of_hidden_la
文件 21676 2017-12-14 10:45 image-denoising-master\graphs\variation_with_size_of_hidden_la
文件 16224 2017-12-14 10:45 image-denoising-master\logistic_sgd.py
文件 13634 2017-12-14 10:45 image-denoising-master\mlp.py
目录 0 2017-12-14 10:45 image-denoising-master\paper\
文件 2633933 2017-12-14 10:45 image-denoising-master\paper\Final_icmla_poster(1)_jp.jpg
文件 1440465 2017-12-14 10:45 image-denoising-master\paper\Final_paper.pdf
相关资源
- 跟老齐学python3.zip
- python机器学习5个数据科学家案例解析
- Fama三因子选股的python实现
- python实现EKF的CTRV模型
- 北京市交通拥堵指数抓取和分析
- python入门笔记推荐
- pygame-1.9.6-cp37-cp37m-win_amd64.zip
- subversion-1.4.6-apache-python.tar
- PythonWin2.7
- Python思维导图.zip255255
- python 写的hants算法代码
- PyInstaller-3.6.tar.gz
- python代码_新冠状病毒仿真器
- Maya Programming with Python Cookbook
- PDFPlumber:从PDF文件提取文字和表格的
- Boost.Python中文文档
- 链路预测 python
-
Pythonsc
ript_full_0.9.0.1.zip - pycharm pymssql python3.6
- matplotlib win32 python2.7画图包
- django简易学生成绩管理
- python+keras+deeplearning
- 基于python的小车走黑线
- python cookbook(第3版)高清中文完整
- 生成Python代码控制流图
- ml-agents-master
- 从视频中分离前景目标的Python & Matl
- 百度图像自动识别程序
- xlrd-1.2.0.tar
- python3.7离线帮助文档英文原版
评论
共有 条评论