Yes or No? I can add data to the network I trained?

2012 2 1
1 个回答
更新时间：2013 9 27
3 次查看（30 天）

回答（1 个）

john john
john john 2012-2-2

0 个投票

okay I trained 290 images which is 30x40 this is for my hand signal recognition.. I resize, make it grayscale and black and white.. since my load image button can recognize well but my snapshot can't recognize some variation I was thinking to get more variation of hand signal then add it to the network I trained..so that every snapshot of my GUI can recognize those variation of position I am right?
wa = imread('C:\Users\Jonas Mamaran\Documents\MATLAB\pray\a\ORIGINAL1.jpg');
x = wa;
y = double(x) / 1000;
data3 = imresize(y,[40 30]);
data4 = rgb2gray(data3);
%new
img2=im2bw(data4,graythresh(data4));
img2=~img2;
BW2 = imfill(img2,'holes');
z = BW2;
z = z(:);
%load network, simulate
load trained_som_20x20m_10ke_30x40p_ae;
input = sim(network,z);
save('input_recognize.mat', 'input');
you think this code can add it to my network?

3 个评论
显示 1更早的评论 隐藏 1更早的评论

Walter Roberson
Walter Roberson 2012-2-3
It might be nice whether where you are, but the area where Jan lives has been dangerously cold for weeks. Jan is busy.
Jan
Jan 2012-2-3
@John: I'm glad to see, that you've spend more details about the problem. Although it is very cold here and the radiator of the house was down for two days now (ran out of oil, after refilling the engine was stuffed by oil mud, I've cleaned it now and the room temperature is going above +10 deg now!), I think (slowly), that you could dare to try if it works. Do you have the impression, that it does not work? Why?

请先登录，再进行评论。

类别

在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

编辑：

Lennart
Lennart
2013-9-27

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by