View on GitHub
AlexNet Structure Reference
AlexNet
public struct AlexNet<Element, Device> : LayerType, Codable where Element : RandomizableType, Device : DeviceTypeAlexNet image classification network.
Batch normalization has been added to this implementation.
-
Declaration
Swift
public var parameterPaths: [WritableKeyPath<`Self`, Tensor<Element, Device>>] { get } -
Declaration
Swift
public var parameters: [Tensor<Element, Device>] { get } -
Determines whether dropout is applied in the classification block
Declaration
Swift
public var isDropoutActive: Bool { get set } -
Creates an AlexNet image classification network with the given number of input channels and classes.
The network expects images with a resolution of 192x192 or higher.
Declaration
Swift
public init(inputChannels: Int, classes: Int)Parameters
inputChannelsNumber of input channesls. Data forwarded through the network must have [batchSize, inputChannels, height, depth] shape.
classesNumber of classes / dimensionality of network output