FlexNN 1
Fully connected neural network built from scratch with flexible n-layer design and multiple activations.
Loading...
Searching...
No Matches
LayerTypes.hpp File Reference

Shared PODs for FlexNN::Layers — LayerType, DType, and per-type Params. More...

#include <cstdint>
#include <type_traits>
Include dependency graph for LayerTypes.hpp:
This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes

struct  FlexNN::Layers::DenseParams
 Parameters for a Dense layer. More...
 
struct  FlexNN::Layers::Conv1DParams
 Parameters for a Conv1D layer. More...
 
struct  FlexNN::Layers::Pool1DParams
 Parameters for pooling layers (Max and Avg share this POD). More...
 
struct  FlexNN::Layers::BatchNormParams
 Parameters for BatchNorm1D. More...
 

Namespaces

namespace  FlexNN
 Namespace for the FlexNN neural network library.
 
namespace  FlexNN::Layers
 

Enumerations

enum class  FlexNN::Layers::LayerType : uint8_t {
  FlexNN::Layers::Dense = 0 , FlexNN::Layers::Conv1D = 1 , FlexNN::Layers::BatchNorm1D = 2 , FlexNN::Layers::MaxPool1D = 3 ,
  FlexNN::Layers::AvgPool1D = 4
}
 Layer kind, stable on-wire (uint8_t). More...
 
enum class  FlexNN::Layers::DType : uint16_t { FlexNN::Layers::F32 = 0 }
 Data type for blobs in model.bin. More...
 

Detailed Description

Shared PODs for FlexNN::Layers — LayerType, DType, and per-type Params.

This header is standalone (no Eigen) so both ModelIO and per-layer headers can include it without pulling heavy dependencies. Values are stable on-wire for model.bin (see LLD_FLEXNN §5, §7, Appendix A).