search

rasmusbergpalm / DeepLearnToolbox

Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.
BSD 2-Clause "Simplified" License
3.8k stars 2.28k forks source link

How can I use NN & CNN for RGB images? #177

Open zhangch3348 opened 7 years ago

zhangch3348 commented 7 years ago

Hi, I have a problem for the NN & CNN. Please help me! One row of the sample data MNIST indicates as a handwritten numeral. Each handwritten numeral is a gray image (one band). But my training datas are lots of RGB images (three bands). How can I use NN & CNN for RGB images?

wajihullahbaig commented 7 years ago

One way is to convert the RGB images to gray scale Or re-write the code to support RGB images. By the way RGB images dont make sense. So just convert them to grayscale using Matlab functions :)

f123gh commented 7 years ago

hye! I need some help regarding Matlab. From the point cloud 3D data I have to extract specific square area for which i know only 2 corner information i.e upper left x,y,z coordinate and bottom right x,y,z coordinates. For this i've to apply some codes in MATLAB through which i get my area of interest(AOI) i.e specific square area which i mentioned above. could you please check my code.Because there accour an error. M= dlmread('sample_data.txt'); x= -7.836000; y= 20.534000; z= 4.541000; x1= -7.095000; y1= 20.013000; z1= 4.675000; discard = M(:,1) < x(1) | M(:,2) < y(2) | M(:,3) < z(3) | ... M(:,1) > x1(1) | M(:,2) > y1(2) | M(:,3) > z1(3) ; Y(discard,:) = [];
Thanks.