https://github.com/iamhankai/mini-dnn-cpp
C++ demo of deep neural networks (MLP, CNN)
https://github.com/iamhankai/mini-dnn-cpp
convolutional-neural-networks cpp deep-neural-networks mnist multi-layer-perceptron
Last synced: about 1 month ago
JSON representation
C++ demo of deep neural networks (MLP, CNN)
- Host: GitHub
- URL: https://github.com/iamhankai/mini-dnn-cpp
- Owner: iamhankai
- License: mit
- Created: 2018-07-16T08:50:09.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2023-12-28T16:39:52.000Z (over 1 year ago)
- Last Synced: 2025-03-20T13:11:13.792Z (about 2 months ago)
- Topics: convolutional-neural-networks, cpp, deep-neural-networks, mnist, multi-layer-perceptron
- Language: C++
- Homepage:
- Size: 2.39 MB
- Stars: 32
- Watchers: 3
- Forks: 11
- Open Issues: 1
-
Metadata Files:
- Readme: readme.md
- License: LICENSE
Awesome Lists containing this project
README
# mini-dnn-cpp
**mini-dnn-cpp** is a C++ demo of deep neural networks. It is implemented purely in C++, whose only dependency, Eigen, is header-only.
## Usage
Download and unzip [MNIST](http://yann.lecun.com/exdb/mnist/) dataset in `mini-dnn-cpp/data/mnist/`.
```shell
mkdir build
cd build
cmake ..
make
```
Run `./demo`.
Result:
simple neural network with 3 FC layers can obtain `0.97+` accuracy on MNIST testset.
LeNet-like CNN can obtain `0.98+` accuracy on MNIST testset.