class
Convolution2D extends Convolution with Layer
Instance Constructors
-
new
Convolution2D(nFilter: Int, kernelSize: List[Int], nChannels: Int = 0, stride: List[Int] = ..., padding: List[Int] = ..., nIn: Option[List[Int]] = scala.None, weightInit: WeightInit = ..., activation: Activation = ..., regularizer: WeightRegularizer = ..., dropOut: Double = 0.0, name: String = "")
Value Members
-
final
def
!=(arg0: AnyRef): Boolean
-
final
def
!=(arg0: Any): Boolean
-
final
def
##(): Int
-
final
def
==(arg0: AnyRef): Boolean
-
final
def
==(arg0: Any): Boolean
-
val
activation: Activation
-
final
def
asInstanceOf[T0]: T0
-
def
clone(): AnyRef
-
def
compile: Layer
-
def
describe(): String
-
val
dropOut: Double
-
final
def
eq(arg0: AnyRef): Boolean
-
def
equals(arg0: Any): Boolean
-
def
finalize(): Unit
-
final
def
getClass(): Class[_]
-
def
hashCode(): Int
-
def
inputShape: List[Int]
-
final
def
isInstanceOf[T0]: Boolean
-
val
name: String
-
final
def
ne(arg0: AnyRef): Boolean
-
final
def
notify(): Unit
-
final
def
notifyAll(): Unit
-
def
outputShape: List[Int]
-
-
def
reshapeInput(nIn: List[Int]): Convolution2D
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
-
def
toString(): String
-
final
def
wait(): Unit
-
final
def
wait(arg0: Long, arg1: Int): Unit
-
final
def
wait(arg0: Long): Unit
-
val
weightInit: WeightInit
Inherited from AnyRef
Inherited from Any
2D convolution for structured image-like inputs. Input should have three dimensions: height (number of rows), width (number of columns), and number of channels. Convolution is over height and width.