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

x/netsaur/src/gpu/network.ts>GPUNetwork

Powerful machine learning, accelerated by WebGPU
denosaurs/netsaur
Go to Latest
class GPUNetwork
implements Network
import { GPUNetwork } from "https://deno.land/x/netsaur@0.1.1/src/gpu/network.ts";

Constructors

new
GPUNetwork(config: NetworkConfig, backend: WebGPUBackend)

Type Parameters

optional
T extends DataType = DataType

Properties

backend: WebGPUBackend
hidden: BaseGPULayer[]
optional
input: InputConfig
output: BaseGPULayer
silent: boolean

Methods

addLayers(layers: LayerConfig[])
backpropagate(output: GPUMatrix, learningRate: number)
feedForward(input: GPUMatrix)
getOutput(): DataArray<T>
initialize(
type: DataType,
inputSize: number,
batches: number,
)
predict(data: DataArray<T>)
train(
datasets: DataSet[],
epochs: number,
batches: number,
learningRate: number,
)