MATLAB Central > MATLAB Newsreader > Neural Network input & output Config. Prob.

Thread Subject: Neural Network input & output Config. Prob.

Subject: Neural Network input & output Config. Prob.

From: dhirendra

Date: 23 Jul, 2008 21:27:42

Message: 1 of 2

Reply to this message

Add author to My Watch List

View original format

Flag as spam

Hi All,

I m Having a problem with NN training & testing for Face
Recognition.
here i want to share with u my input & output pattern for NN & want
suggestion of modifications...

I m having 100 images in which set of 10 images belong to a
particular person,so 10 person are there.
If i process these 100 images with pca & give input to NN then input
pattern goes columnwise-
1-1 1-2 1-3......after 10 images of first person...2-1 2-2 2-3.....
& output is like
1 1 1...after 10 values...2 2 2... likewise

but the problem is that the NN is getting trained but testing fails.

whts the solution of it?
should i train Setwise(set of 10 images for each person) & save
weights then test one by one with each save weights.
plz help guys.

Regards
Dhirendra

Subject: Neural Network input & output Config. Prob.

From: Greg Heath

Date: 24 Jul, 2008 01:13:59

Message: 2 of 2

Reply to this message

Add author to My Watch List

View original format

Flag as spam

On Jul 23, 5:27=A0pm, dhirendra <dhirendraii...@gmail.com> wrote:
> Hi All,
>
> =A0 I m Having a problem with NN training & testing for Face
> Recognition.
> =A0 here i want to share with u my input & output pattern for NN & want
> suggestion of modifications...
>
> =A0I m having 100 images in which set of 10 images belong to a
> particular person,so 10 person are there.
> =A0If i process these 100 images with pca & give input to NN then input
> pattern goes columnwise-
> =A01-1 1-2 1-3......after 10 images of first person...2-1 2-2 2-3.....
> =A0& output is like
> 1 1 1...after 10 values...2 2 2... likewise
>
> but the problem is that the NN is getting trained but testing fails.
>
> whts the solution of it?

The size of the input matrix is [n 100] ... what is n?

The size of the output matrix should be [10 100]:

columns 1 to 10 =3D [ 1 0 0 0 0 0 0 0 0 0]'
=2E..
columns 99 to 100 =3D [ 0 0 0 0 0 0 0 0 0 1]'

> should i train Setwise(set of 10 images for each person) & save
> weights then test one by one with each save weights.

If you don't have more data you should train with 9 images
per person and use the other image for unbiased testing.

See my post on pretraining advice and make sure that
you do not overtrain an overparameterized net.

Hope this helps.

Greg

Tags for this Thread

Add a New Tag:

Separated by commas
Ex.: root locus, bode

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

Feed for this Thread

E-mail this page to a colleague

Public Submission Policy
NOTICE: Any content you submit to MATLAB Central, including personal information, is not subject to the protections which may be afforded information collected under other sections of The MathWorks, Inc. Web site. You are entirely responsible for all content that you upload, post, e-mail, transmit or otherwise make available via MATLAB Central. The MathWorks does not control the content posted by visitors to MATLAB Central and, does not guarantee the accuracy, integrity, or quality of such content. Under no circumstances will The MathWorks be liable in any way for any content not authored by The MathWorks, or any loss or damage of any kind incurred as a result of the use of any content posted, e-mailed, transmitted or otherwise made available via MATLAB Central. Read the complete Disclaimer prior to use.