tensor-safe-0.1.0.1: Create valid deep neural network architectures

Safe HaskellNone
LanguageHaskell2010

TensorSafe.Layers.Conv2D

Description

This module declares the 2D convolutional layer data type.

Synopsis

Documentation

data Conv2D :: Nat -> Nat -> Nat -> Nat -> Nat -> Nat -> Type where Source #

A 2D Convolutional layer

Constructors

Conv2D :: Conv2D channels filters kernelRows kernelColumns strideRows strideColumns 
Instances
Show (Conv2D a b c d e f) Source # 
Instance details

Defined in TensorSafe.Layers.Conv2D

Methods

showsPrec :: Int -> Conv2D a b c d e f -> ShowS #

show :: Conv2D a b c d e f -> String #

showList :: [Conv2D a b c d e f] -> ShowS #

(KnownNat channels, KnownNat filters, KnownNat kernelRows, KnownNat kernelColumns, KnownNat strideRows, KnownNat strideColumns) => Layer (Conv2D channels filters kernelRows kernelColumns strideRows strideColumns) Source # 
Instance details

Defined in TensorSafe.Layers.Conv2D

Methods

layer :: Conv2D channels filters kernelRows kernelColumns strideRows strideColumns Source #

compile :: Conv2D channels filters kernelRows kernelColumns strideRows strideColumns -> InputShape -> CNetwork Source #