Package org.jetbrains.kotlinx.dl.api.core.model

Functions

resnet101

fun resnet101(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet101 architecture as a Functional model.

resnet101Light

fun resnet101Light(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet101 architecture without BatchNorm layers as a Functional model.

resnet101v2

fun resnet101v2(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet101V2 architecture as a Functional model.

resnet101v2Light

fun resnet101v2Light(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet101V2 architecture without BatchNorm layers as a Functional model.

resnet152

fun resnet152(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet152 architecture as a Functional model.

resnet152Light

fun resnet152Light(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet152 architecture without BatchNorm layers as a Functional model.

resnet152v2

fun resnet152v2(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet152V2 architecture as a Functional model.

resnet152v2Light

fun resnet152v2Light(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet152V2 architecture without BatchNorm layers as a Functional model.

resnet50

fun resnet50(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet50 architecture as a Functional model.

resnet50Light

fun resnet50Light(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet50 architecture without BatchNorm layers as a Functional model.

resnet50v2

fun resnet50v2(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet50V2 architecture as a Functional model.

resnet50v2Light

fun resnet50v2Light(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Functional

Instantiates the ResNet50V2 architecture without BatchNorm layers as a Functional model.

vgg16

fun vgg16(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Sequential

Instantiates the VGG16 model.

vgg19

fun vgg19(imageSize: Long = 224, numberOfClasses: Int = 10, numberOfInputChannels: Long = 3, lastLayerActivation: Activations = Activations.Linear): Sequential

Instantiates the VGG19 model.