diff --git a/Norse/requirements.txt b/Norse/requirements.txt new file mode 100755 index 0000000000000000000000000000000000000000..bc8da77c31fa322923b1bd36a04ba8cce4e72567 --- /dev/null +++ b/Norse/requirements.txt @@ -0,0 +1,2 @@ +matplotlib +norse \ No newline at end of file diff --git a/README.md b/README.md index 16d49939ad761ef238ae6a8a405ace6f6e25b8a8..02cc6587955b9135181ade8be947f01bec77d3d6 100644 --- a/README.md +++ b/README.md @@ -36,6 +36,16 @@ For example: to run MNIST simulation without compression and reinforcement: In the `apps` folder, you will find the source code for each simulation, where you can change the architecture and the network parameters or activate the [layerwise compression](https://gitlab.univ-lille.fr/hammouda.elbez/progressive-layer-based-compression-for-convolutional-spiking-neural-network/-/blob/main/CSNN-Simulator/apps/Mnist.cpp#L21). +### How to use Norse +First, install the required libraries: + + python install -r requirements.txt + +To run a simulation: + + python [name_dataset].py + +Each file runs each configuration ten times. You can change the parameters at the beginning of each file. ## Going from CSNN to SpiNNaker First, run the simulation of the two dense layers using CSNN: