yaopu / cnn_cpu

Referenz-Implementierung eines CNN mittels C++ ohne Parallelisierung.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

cnn_cpu

Reference-Implementation of a Convolutional Neural Network from scratch using C++ without parallelization.

Used libraries: Armadillo, Google Test

Usage:

1. Clone repository git clone https://github.com/felixp98/cnn_cpu.git
2. Install Armadillo version 8.4 or higher (see below).
3. Create a build directory, e.g. mkdir cmake_build
4. Update the correct path for the MNIST data in cnn_reference_test.cpp
5. cd into the build directory and generate build files: cmake ../
6. Build the project using make
7. Train and test the model using ./cnn_reference_test

Armadillo Installation:

  1. Install Armadillo prerequisities: sudo apt install cmake libopenblas-dev liblapack-dev
  2. Download newest Armadillo version: http://arma.sourceforge.net/download.html
  3. cd into extracted directory cd arma*
  4. Generate build files: cmake .
  5. make
  6. sudo make install

About

Referenz-Implementierung eines CNN mittels C++ ohne Parallelisierung.


Languages

Language:C++ 95.9%Language:CMake 4.1%