Crates.io | reverse |
lib.rs | reverse |
version | 0.2.2 |
source | src |
created_at | 2021-08-01 23:18:03.622099 |
updated_at | 2021-08-07 05:10:03.766651 |
description | Reverse mode automatic differentiation. |
homepage | |
repository | https://github.com/al-jshen/reverse |
max_upload_size | |
id | 430175 |
size | 40,365 |
Zero-dependency crate for reverse mode automatic differentiation in Rust.
To use this in your crate, add the following to Cargo.toml
:
[dependencies]
reverse = "0.2"
use reverse::*;
fn main() {
let tape = Tape::new();
let a = tape.add_var(2.5);
let b = tape.add_var(14.);
let c = (a.sin().powi(2) + b.ln() * 3.) - 5.;
let gradients = c.grad();
assert_eq!(gradients.wrt(&a), (2. * 2.5).sin());
assert_eq!(gradients.wrt(&b), 3. / 14.);
}
The main type is Var<'a>
, so you can define functions that take this as an input (possibly along with other f64
arguments) and also returns this as an output, and the function will be differentiable. For example:
use reverse::*;
fn main() {
let tape = Tape::new();
let params = tape.add_vars(&[5., 2., 0.]);
let data = [1., 2.];
let result = diff_fn(¶ms, &data);
let gradients = result.grad();
println!("{:?}", gradients.wrt(¶ms));
}
fn diff_fn<'a>(params: &[Var<'a>], data: &[f64]) -> Var<'a> {
params[0].powf(params[1]) + data[0].sin() - params[2].asinh() / data[1]
}