https://github.com/greatgamedota/cnn-in-cpp
CNN implementation in C++ categorizing the MNIST data set
https://github.com/greatgamedota/cnn-in-cpp
algorithms cnn convolutional-neural-networks machine-learning math neural-network
Last synced: 11 months ago
JSON representation
CNN implementation in C++ categorizing the MNIST data set
- Host: GitHub
- URL: https://github.com/greatgamedota/cnn-in-cpp
- Owner: GreatGameDota
- License: mit
- Created: 2019-09-17T12:58:13.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2019-09-24T20:16:36.000Z (almost 7 years ago)
- Last Synced: 2025-07-03T08:44:11.212Z (about 1 year ago)
- Topics: algorithms, cnn, convolutional-neural-networks, machine-learning, math, neural-network
- Language: C++
- Homepage:
- Size: 715 KB
- Stars: 15
- Watchers: 1
- Forks: 3
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Convolutional Neural Network in C++
Implemented following [Alejandro Escontrela](https://github.com/Alescontrela)'s Towards Data Science Medium Article ["Convolutional Neural Networks from the ground up"](https://towardsdatascience.com/convolutional-neural-networks-from-the-ground-up-c67bb41454e1) and [Python Implementation](https://github.com/Alescontrela/Numpy-CNN) on Github
Disclaimer: This project is slow and was made mostly for fun and learning
This Network is built and trained for the MNIST data set.
The dimensions of this model are:
8 filters for the 2 convolution layers then 1 maxpool before a 2 layer fully connected layer.
### Run this program
To run this program simply have MinGW C++ compiler installed and clone this repo:
```shell
> git clone
```
Then build and run the exe:
```shell
> g++ *.cpp */*.cpp -o main -Ofast
> ./main
```