Need help with ofxCcv?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

kylemcdonald
124 Stars 21 Forks Other 44 Commits 6 Opened issues

Description

libccv addon for openFrameworks

Services available

!
?

Need anything else?

Contributors list

# 6,273
osx
openfra...
MATLAB
Lua
16 commits
# 31,120
Jupyter...
C++
HTML
dcgan
16 commits
# 8,200
emscrip...
osx
Raspber...
openfra...
4 commits
# 13,180
Linux
libgdx
html5
C++
3 commits

ofxCcv

Currently the binary library is only precompiled for for 32-bit and 64-bit OSX (thanks to Gene Kogan). Additional contributions for face recognition come from Antimodular Research.

After cloning the repository, you will need to run

./setup.sh
to download the pre-trained ImageNet classifier.

Setting up CUDA support

After installing CUDA and recompiling ccv with CUDA support, replace

ccv.a
in the
libs
folder with your new static library. Then make a copy of the following CUDA libraries adjacent to
ccv.a
:
libcublas_static.a
,
libcudart_static.a
,
libculibos.a
. Rename them all to remove the
lib
prefix. Include them in the linking step. Finally, add GSL to the linker step, too. On OSX after installing GSL with Homebrew, this means adding
-L/usr/local/Cellar/gsl/1.16/lib
and
-lgsl
. After all of this, classification of a single 640x480 image should drop from 750ms to 400ms.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.