Skip to main content
Using Deno in production at your company? Earn free Deno merch.
Give us feedback
Module

x/netsaur/backends/gpu/backend.ts>GPUBackend

Powerful machine learning, accelerated by WebGPU
Go to Latest
class GPUBackend
implements Backend
import { GPUBackend } from "https://deno.land/x/netsaur@0.1.5/backends/gpu/backend.ts";

Constructors

new
GPUBackend(config: NetworkConfig, backend: WebGPUBackend)

Type Parameters

optional
T extends DataType = DataType

Properties

backend: WebGPUBackend
imported: boolean
optional
input: Size
layers: GPULayer[]
output: GPULayer
silent: boolean

Methods

addLayer(layer: Layer): void
backpropagate(output: GPUMatrix, rate: number)
initialize(
inputSize: Size,
batches: number,
type: DataType,
)
save(_str: string): void
setCost(activation: Cost): void
toJSON(): Promise<NetworkJSON>
train(
datasets: DataSet[],
epochs?,
batches?,
rate?,
)