This library provides multiple tensor implementations hidden behind an easy to use API that supports reverse mode automatic differentiation.
## Features
* Flexible ✨
* CPU + GPU 🙏
* Multi-Threads 🚀
* Intuitive Usage 😌
* No Global State 🚫
* Multiple Backends 🦾
* Reverse Mode Autodiff 🔥
### Backends
For now, only two backends are implementated, but adding new ones should be easy.
* [X] Pytorch using [tch-rs](https://github.com/LaurentMazare/tch-rs)
* [X] 100% Rust backend using [ndarray](https://github.com/rust-ndarray/ndarray)
* [ ] Tensorflow using [tensorflow-rust](https://github.com/tensorflow/rust)
* [ ] ...
## Usage
### Basic
This library separates data from tensors, where the former is used to create new tensors and serialize/deserialize data, and the later is used to execute tensor operations.