TensorSafe.Layer

This module defines the Layer class from which all Layers should have instances of.

Documentation

type InputShape = Maybe String

Auxiliary type for Input Shape parameter

class Layer x

Defines that a type is a Layer Each layer can be compilated into a specific CNetwork expression which can later be used to generate code to a specific backend.

Minimal complete definition

compile, layer

Instances

Layer Flatten

Defined in TensorSafe.Layers.Flatten

Methods

layer :: Flatten

compile :: Flatten -> InputShape -> CNetwork

Layer Relu

Defined in TensorSafe.Layers.Relu

Methods

layer :: Relu

compile :: Relu -> InputShape -> CNetwork

Layer Sigmoid

Defined in TensorSafe.Layers.Sigmoid

Methods

layer :: Sigmoid

compile :: Sigmoid -> InputShape -> CNetwork

(KnownNat input, KnownNat output) => Layer (Dense input output)

Defined in TensorSafe.Layers.Dense

Methods

layer :: Dense input output

compile :: Dense input output -> InputShape -> CNetwork

(KnownNat rate, KnownNat seed) => Layer (Dropout rate seed)

Defined in TensorSafe.Layers.Dropout

Methods

layer :: Dropout rate seed

compile :: Dropout rate seed -> InputShape -> CNetwork

KnownNat units => Layer (LSTM units b)

Defined in TensorSafe.Layers.LSTM

Methods

layer :: LSTM units b

compile :: LSTM units b -> InputShape -> CNetwork

ValidNetwork ls ss => Layer (INetwork ls ss)

This instance of INetwork as a Layer makes possible nesting INetworks

Defined in TensorSafe.Network

Methods

layer :: INetwork ls ss

compile :: INetwork ls ss -> InputShape -> CNetwork

(KnownNat kernelRows, KnownNat kernelColumns, KnownNat strideRows, KnownNat strideColumns) => Layer (MaxPooling kernelRows kernelColumns strideRows strideColumns)

Defined in TensorSafe.Layers.MaxPooling

Methods

layer :: MaxPooling kernelRows kernelColumns strideRows strideColumns

compile :: MaxPooling kernelRows kernelColumns strideRows strideColumns -> InputShape -> CNetwork

(KnownNat channels, KnownNat filters, KnownNat kernelRows, KnownNat kernelColumns, KnownNat strideRows, KnownNat strideColumns) => Layer (Conv2D channels filters kernelRows kernelColumns strideRows strideColumns)

Defined in TensorSafe.Layers.Conv2D

Methods

layer :: Conv2D channels filters kernelRows kernelColumns strideRows strideColumns

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

compile :: Layer x => x -> InputShape -> CNetwork

Given the layer and a optional inputShape generates a CNetwork structure

layer :: Layer x => x

The layer type