This repo is the CUDA implementation of SNNs trained the hybrid macro/micro level backpropagation, modified based on zhxfl for spiking neuron networks.

The paper Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks is accepted by NeurIPS 2018.

Contact [email protected] if you have any questions or concerns.

• opencv
• cuda (suggest cuda 8.0)

You can compile the code on windows or linux.

• linux: /usr/local/cuda/samples/common/inc/ (For include file "helper_cuda"); /usr/local/include/opencv/ (Depend on situation)
• windows: X:/Program Files (x86) /NVIDIA Corporation/CUDA Samples/v6.5/common/inc (For include file "helper_cuda"); X:/Program Files/opencv/vs2010/install/include (Depend on situation)

• linux: /usr/local/lib/
• windows: X:/Program Files/opencv/vs2010/install/x86/cv10/lib (Depend on situation)

• opencv_core
• opencv_highgui
• opencv_imgproc
• opencv_imgcodecs (need for opencv3.0)
• cublas
• curand
• cudadevrt

The repo requires CUDA 8.0+ to run.

Please install the opencv and cuda before hand.

Install CMake and OpenCV

$ sudo apt-get install cmake libopencv-dev 

Checkout and compile the code:

$ git clone https://github.com/jinyyy666/mm-bp-snn.git
$ cd mm-bp-snn
$ mkdir build
$ cd build
$ cmake ..
$ make -j

• capability 6.0 for Titan XP, which is used for the authors.

Get the MNIST dataset:

$ cd mm-bp-snn/mnist/
$ ./get_mnist.sh

Get the N-MNIST dataset by the link. Then unzip the ''Test.zip'' and ''Train.zip''.

Run the matlab code: NMNIST_Converter.m in nmnist/

• MNIST

$ cd mm-bp-snn
$ ./build/CUDA-SNN 6 1

• N-MNIST

$ cd mm-bp-snn
$ ./build/CUDA-SNN 7 1

• For Spiking-CNN, you need to enable the #define SPIKING_CNN in main.cpp, and recompile.

$ cd mm-bp-snn
$ ./build/CUDA-SNN 6 1

Do the following to set up compilation environment.

• Install Visual Stidio and OpenCV.
• When you create a new project using VS, You can find NVIDIA-CUDA project template, create a cuda-project.
• View-> Property Pages-> Configuration Properties-> CUDA C/C++ -> Device-> Code Generation-> compute_60,sm_60
• View-> Property Pages-> Configuration Properties-> CUDA C/C++ -> Common-> Generate Relocatable Device Code-> Yes(-rdc=true)
• View-> Property Pages-> Configuration Properties-> Linker-> Input-> Additional Dependencies-> libraries(-l)
• View-> Property Pages-> Configuration Properties-> VC++ Directories-> General-> Library search path(-L)
• View-> Property Pages-> Configuration Properties-> VC++ Directories-> General-> Include Directories(-I)

• The SNNs are implemented in terms of layers. User can config the SNNs by using configuration files in Config/
• The program will save the best test result and save the network weight in the file "Result/checkPoint.txt", If the program exit accidentally, you can continue the program form this checkpoint.
• The log for the reported performance of the three datasets and the correspoding checkout point files can be found in Result folder.