Expand description
Ergonomics & safety focused deep learning in Rust. Main features include:
- Tensor library, complete with const generic shapes, activation functions, and more.
- Safe & Easy to use neural network building blocks.
- Standard deep learning optimizers such as Sgd and Adam.
- Reverse mode auto differentiation[1] implementation.
Modules
Collection of traits to describe Nd arrays.
Provides implementations for modifying Nd arrays on the CPU.
Implementations of Gradient tapes and generic gradient containers.
Standard loss functions such as mse, mae, cross entropy, and more.
Provides some generic functions to save Nd arrays in the .npy format.
Contains all public exports.
Implementations of all operations for tensors, including activations, binary operations, and other methods.