Forums before death by AOL, social media and spammers... "We can't have nice things"
|    comp.ai    |    Awaiting the gospel from Sarah Connor    |    1,954 messages    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
|    Message 1,791 of 1,954    |
|    dhirendra to All    |
|    Neural Network input & output Config. Pr    |
|    24 Jul 08 10:20:15    |
      From: dhirendraiiitm@gmail.com              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              [ comp.ai is moderated ... your article may take a while to appear. ]              --- SoupGate-Win32 v1.05        * Origin: you cannot sedate... all the things you hate (1:229/2)    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
(c) 1994, bbs@darkrealms.ca