Module layers 

Neural network layers implementation

This module provides implementations of various neural network layers such as dense (fully connected), attention, convolution, pooling, etc. Layers are the fundamental building blocks of neural networks.

Re-exports

pub use conv::Conv2D;

pub use dense::Dense;

pub use dropout::Dropout;

pub use normalization::BatchNorm;

pub use normalization::LayerNorm;

pub use recurrent::LSTM;

Modules

conv

Convolutional neural network layers implementation

dense

Dense (fully connected) layer implementation

dropout

Dropout layer implementation

normalization

Normalization layers implementation

recurrent

Recurrent layer implementations

Structs

LayerInfo

Information about a layer for visualization purposes

Sequential

Sequential container for neural network layers

Enums

LayerConfig

Configuration enum for different types of layers

Traits

Layer

Base trait for neural network layers

ParamLayer

Trait for layers with parameters (weights, biases)