mirror of
https://github.com/lordmathis/CUDANet.git
synced 2025-11-06 17:54:27 +00:00
41 lines
663 B
Markdown
41 lines
663 B
Markdown
# CUDANet
|
|
|
|
:warning: Work in progress
|
|
|
|
Convolutional Neural Network inference library running on CUDA.
|
|
|
|
## Features
|
|
|
|
- [x] Input layer
|
|
- [x] Dense (fully-connected) layer
|
|
- [x] Conv2d layer
|
|
- [x] Max pooling
|
|
- [x] Average pooling
|
|
- [x] Concat layer
|
|
- [x] Sigmoid activation
|
|
- [x] ReLU activation
|
|
- [x] Softmax activation
|
|
- [ ] Load weights from file
|
|
|
|
## Usage
|
|
|
|
**requirements**
|
|
- [cmake](https://cmake.org/)
|
|
- [CUDA](https://developer.nvidia.com/cuda-downloads)
|
|
- [Google Test](https://github.com/google/googletest) (for testing only)
|
|
|
|
**build**
|
|
|
|
```sh
|
|
mkdir build
|
|
cd build
|
|
cmake -S ..
|
|
make
|
|
```
|
|
|
|
**build and run tests**
|
|
|
|
```sh
|
|
make test_main
|
|
./test/test_main
|
|
``` |