Closed synchro-- closed 9 years ago
the face detector might be a little outdated. try the ones in this repo: https://github.com/e-lab/torch7-demos
Ah yes it seemed to be a little old. Thank you. Btw if now I do from terminal (in the face-detector-elab folder) :
qlua run.lua ==> processing options qlua: /usr/local/share/lua/5.1/torch/File.lua:232: read error: read 1 blocks instead of 25602 stack traceback: [C]: at 0x7f699fd06620 [C]: in function 'read' /usr/local/share/lua/5.1/torch/File.lua:232: in function </usr/local/share/lua/5.1/torch/File.lua:163>
And if I run it inside qlua :
==> processing options /usr/local/share/lua/5.1/pl/lapp.lua:321: attempt to get length of local 'arg' (a nil value) stack traceback: /usr/local/share/lua/5.1/pl/lapp.lua:321: in function 'lapp' run.lua:26: in main chunk
Actually there are errors like that for every demo.
i removed the face detector demo, it was broken and not working.
Ok, sorry for opening too much issues but I was searching for some working demo for face detection to actually looking at the code and learn some trick.
When I was TA for Davi's class I copied Clement's face-detector demo and fixed it so it runs on the new torch / lua:
you can take a look at person-detector demo which is almost the same as face-detector. The network there doesn't perform well but there are many tricks.
Thanks @Aysegul @jonathantompson I'll take a look at both
Ok @soumith the code works, I had something old for sure. Apart from that, are this and the person-detector good for learning how to use the multiscale pyramid technique? I mean for a newbie. Sure there are things more complex, like the road-net for example. @Aysegul
I think they are good. You can display the middle steps with image.display to see what pyramid does.
How can I run the file run.lua in the facedetector demo? I should run it with qlua that has qt packege preloaded of course. So:
So I tried qlua first and then If I do : require 'inline' the first time it gives me the same error, the second time it works. (why?) . Anyway after I run it:
No matter what it gaves me the error above. Thank you for helping