Conv2D
class Conv2D(filters: Long, kernelSize: LongArray, strides: LongArray, dilations: LongArray, activation: Activations, kernelInitializer: Initializer, biasInitializer: Initializer, kernelRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, useBias: Boolean, name: String) : AbstractConv
Content copied to clipboard
2D convolution layer (e.g. spatial convolution over images).
This layer creates a convolution kernel that is convolved (actually cross-correlated) with the layer input to produce a tensor of outputs. Finally, the activation
is applied to the outputs as well.
It expects input data of size (N, H, W, C)
where
N - batch size
H - height
W - width
C - number of channels
Constructors
Conv2D
Link copied to clipboard
fun Conv2D(filters: Long = 32, kernelSize: LongArray = longArrayOf(3, 3), strides: LongArray = longArrayOf(1, 1, 1, 1), dilations: LongArray = longArrayOf(1, 1, 1, 1), activation: Activations = Activations.Relu, kernelInitializer: Initializer = HeNormal(), biasInitializer: Initializer = HeUniform(), kernelRegularizer: Regularizer? = null, biasRegularizer: Regularizer? = null, activityRegularizer: Regularizer? = null, padding: ConvPadding = ConvPadding.SAME, useBias: Boolean = true, name: String = "")
Content copied to clipboard
Creates Conv2D object.
Functions
buildFromInboundLayers
Link copied to clipboard
Extend this function to define variables in layer.
computeOutputShape
Link copied to clipboard
Computes output shape, based on inputShape and Layer type.
computeOutputShapeFromInboundLayers
Link copied to clipboard
Computes output shape, based on input shapes of inbound layers.
forward
Link copied to clipboard
Properties
activation
Link copied to clipboard
activityRegularizer
Link copied to clipboard
biasInitializer
Link copied to clipboard
biasRegularizer
Link copied to clipboard
biasShapeArray
Link copied to clipboard
hasActivation
Link copied to clipboard
inboundLayers
Link copied to clipboard
isTrainable
Link copied to clipboard
kernelInitializer
Link copied to clipboard
kernelRegularizer
Link copied to clipboard
kernelShapeArray
Link copied to clipboard
kernelSize
Link copied to clipboard
outboundLayers
Link copied to clipboard
outputShape
Link copied to clipboard
padding
Link copied to clipboard
paramCount
Link copied to clipboard
parentModel
Link copied to clipboard