How can I improve my NN results?
1 view (last 30 days)
Show older comments
I selected the training values from corrupted parts' neighbors, and use them as a training data(input data). Target data is their neighbors' pixels.
TRT(2*4574): 162 163 164
37 37 37 ...
kkT(1*4574): 0.341176470588235 0.341176470588235 0.325490196078431 0.356862745098039 ...
net=newfit(TRT,kkT,200)
net=train(net,TRT,kkT)
output=net(TRTIT)
I take some results:
>> output=net(TRTIT) %prediction
output =
0.4295
>> I(158,40)%original
ans =
0.4235
How can I improve my results? Is that training good for image inpainting case? I am really looking forward your answers, Regards,
0 Comments
Answers (0)
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!