Comments (9)
the face detector might be a little outdated. try the ones in this repo:
https://github.com/e-lab/torch7-demos
from 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.
from demos.
i removed the face detector demo, it was broken and not working.
from demos.
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.
from demos.
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:
https://github.com/jonathantompson/geiger_facedetector
from demos.
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.
from demos.
Thanks @Aysegul @jonathantompson
I'll take a look at both
from demos.
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
from demos.
I think they are good. You can display the middle steps with image.display to see what pyramid does.
from demos.
Related Issues (20)
- how to set nstates and filtsize in recognize face
- Convolution layers lose col/row: train-a-digit-classifier/train-on-mnist.lua HOT 2
- require 'data': module data not found
- Person detection error HOT 2
- I cannot downloading the image data for face detector HOT 2
- I need the rgb to yuv script, but it doesn't work.
- profiling/linear-cpu.lua uses cunn HOT 2
- How to communicate between torch and some other program language? HOT 3
- demos contain errors, please fix them or indicate how we can fix them
- why train-on-cifar.lua always stops at the very 4th epoch?
- sorry
- Help! CAN NOT LOAD more than 70 images?
- /usr/lib64/lua/5.1/libpng.so: undefined symbol: png_set_longjmp_fn on train-face-detector demo HOT 7
- Torch ffi is depracated on person detector HOT 1
- Tracker is slow
- Normalization of Error (f) and grad param HOT 1
- error with luarocks install camera HOT 3
- person-detector camera error
- uninitialised variable train-on-cifar.lua
- ASGD optimization call uses uninitialized variable nbTrainingPatches
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from demos.