Caffe framework
Description
Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by the Berkeley Vision and Learning Center (BVLC) and by community contributors.
License
Caffe is released under the BSD 2-Clause license.
Usage
Upcoming modulesystem change alert!
Due to large number of applications and their versions it is not practical to keep them explicitly listed at our wiki pages. Therefore an upgrade of modulefiles is underway. A feature of this upgrade will be the existence of default module for every application. This default choice does not need version number and it will load some (usually latest) version.
You can test the new version now by adding a line
source /cvmfs/software.metacentrum.cz/modulefiles/5.1.0/loadmodules
to your script before loading a module. Then, you can list all versions of caffe and load default version of caffe as
module avail caffe/ # list available modules module load caffe # load (default) module
If you wish to keep up to the current system, it is still possible. Simply list all modules by
module avail caffe
and choose explicit version you want to use.
MetaCentrum provides several version of caffe framework:
CPU version: caffe2016-cpu GPU version: caffe2016-gpu GPU + cuDNN version: caffe-mar2017-cudnn
Please note that the GPU version is faster than the CPU version.
Moreover, testing of our MetaCentrum builds has shown that the GPU version compiled with cuDNN library is several times faster than the GPU version without it.
However, cuDNN is only supported on GPU clusters (see GPU clusters), on other GPU clusters it is only possible to run the GPU version without it.
Our versions of Caffe include pycaffe interface. After loading Caffe module type
python import caffe
and you can immediately start.
Documentation
http://caffe.berkeleyvision.org/tutorial/