This repository has been archived on 2019-09-17 . You can view files and clone it, but cannot push or open issues or pull requests.
3cbf1a128151ce374cb6219d044ebf0e2364dd3a
Using in-place layers makes it impossible to see the state of an individual layer, so this script rewrites them into each having their own output layer.
Functional MRI for Neural Networks
An attempt to create real-time in depth visualisation for neural networks.
Requirements
The following programs/libraries need to be installed on your system:
- CMake (at least 3.1)
- Caffe
- Google log (glog)
- OpenCV
- Boost System
- PNG++
Note that most of these are dependencies of Caffe, and thus will probably already be on your system.
Building
The build process is based on CMake. This means you can easily create a build as follows. Starting from the project root:
mkdir build && cd build
cmake ..
make
Compilation is a little slow due to the inclusion of Boost.
Description
Languages
C++
73.7%
CMake
26.1%
Shell
0.2%