auto_diff/lib.rs
1#![allow(dead_code)]
2#![allow(unused_variables)]
3//#![no_std]
4//! An auto-difference library
5//! =============================================================
6//!
7//!
8//! Introduction
9//! ------------
10//! This is yet another auto-difference library for deep neural network.
11//! The focus is easy on use and dynamic computation graph building.
12//!
13//! Install
14//! ------------
15//! Add auto-diff = "0.5" to the \[dependencies\] section of your project Cargo.toml file.
16//!
17//! Features
18//! ------------
19//! The forward operators support a commonly used set, including:
20//!
21//! 1. getter/setter,
22//! 2. index and slicing,
23//! 3. +, -, *, / and matmul,
24//! 4. speciall functions,
25//! 5. statistics,
26//! 6. linear algebra,
27//! 7. random number generator.
28//!
29//! The corresponding gradient is work-in-progress.
30//!
31//! One feature of auto-diff is the auto-difference is in background
32//! and don't get in your way if only forward calculation is needed.
33//! Thus it can be used without syntax like variable place holder.
34//!
35//! Example
36//! ------------
37//!
38
39
40pub mod var;
41pub mod op;
42pub mod optim;
43pub mod err;
44
45pub use var::{Var};
46pub use err::AutoDiffError;
47
48pub mod compute_graph;
49pub mod collection;
50pub mod var_inner;
51#[cfg(feature = "use-serde")]
52pub mod serde;