Dropout2DLayer | /src/core/api/layers.ts | netsaur@0.2.12

Module

x/netsaur/src/core/api/layers.ts>Dropout2DLayer

Powerful machine learning, accelerated by WebGPU

denosaurs/netsaur

Go to Latest

error.ts

ActivationError

IncompatibleRankError

ActivationLayerConfig

BatchNormLayerConfig

Conv2DLayerConfig

ConvTranspose2DLayerConfig

OneCycleSchedulerConfig

function Dropout2DLayer

import { Dropout2DLayer } from "https://deno.land/x/netsaur@0.2.12/src/core/api/layers.ts";

Dropout2DLayer(config: DropoutLayerConfig): Layer

Creates a dropout layer. Dropout is a regularization technique for reducing overfitting. The technique temporarily drops units (artificial neurons) from the network, along with all of those units' incoming and outgoing connections. See https://en.wikipedia.org/wiki/Dropout_(neural_networks)

Parameters

config: DropoutLayerConfig

Returns

Layer