https://github.com/andreytkachenko/yarnn

Yet Another rust Neural Network framework
https://github.com/andreytkachenko/yarnn

convolutional-neural-networks framework machine-learning neural-networks rust

Last synced: 9 months ago
JSON representation

Yet Another rust Neural Network framework

• Host: GitHub
• URL: https://github.com/andreytkachenko/yarnn
• Owner: andreytkachenko
• License: mit
• Created: 2019-02-21T13:29:38.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2022-03-17T18:20:55.000Z (about 4 years ago)
• Last Synced: 2024-04-25T21:43:43.485Z (almost 2 years ago)
• Topics: convolutional-neural-networks, framework, machine-learning, neural-networks, rust
• Language: Rust
• Homepage:
• Size: 39.9 MB
• Stars: 14
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
## Yet Another Rust Neural Network framework aka YARNN

Inspired by `darknet` and `leaf`

## What it can right now:

 * not requires `std` (only `alloc` for tensor allocations, bump allocator is ok, so it can be compiled to stm32f4 board)

 * available layers: `Linear`, `ReLu`, `Sigmoid`, `Softmax`(no backward), `Conv2d`, `ZeroPadding2d`, `MaxPool2d`, `AvgPool2d`(no backward), `Flatten`

 * available optimizers: `Sgd`, `Adam`, `RMSProp`

 * available losses: `CrossEntropy`(no forward), `MeanSquareError`

 * available backends: `Native`, `NativeBlas`(no convolution yet)

## What it will can (I hope):

### 1st stage:

 * example of running `yarnn` in browser using `WASM`

 * example of running `yarnn` on `stm32f4` board

 * finish `AvgPool2d` backpropogation

 * add `Dropout` layer

 * add `BatchNorm` layer

 * convolution with BLAS support 

### 2nd stage:

 * `CUDA` support

 * `OpenCL` support

### 3rd stage:

 * `DepthwiseConv2d` layer

 * `Conv3d` layer

 * `Deconv2d` layer

 * `k210` backend

## Model definition example

```rust

use yarnn::model;

use yarnn::layer::*;

use yarnn::layers::*;

model! {

    MnistConvModel (h: u32, w: u32, c: u32) {

        input_shape: (c, h, w),

        layers: {

            Conv2d {

                filters: 8

            },

            ReLu,

            MaxPool2d {

                pool: (2, 2)

            },

            Conv2d {

                filters: 8

            },

            ReLu,

            MaxPool2d {

                pool: (2, 2)

            },

            Flatten,

            Linear {

                units: 10

            },

            Sigmoid

        }

    }

}

```

## Contributors are welcome