Package org.nd4j.linalg.api.ops.impl.layers.convolution

Class Summary

Class	Description
AvgPooling2D	Average Pooling2D operation
BatchNorm	BatchNorm operation
BatchNormDerivative	BatchNormDerivative operation
Col2Im	Col2Im operation.
Conv1D	Conv2D operation
Conv2D	Conv2D operation
Conv2DDerivative	Conv2DDerivative operation
Conv3D	Conv3D operation
Conv3DDerivative	Conv3DDerivative operation
DeConv2D	DeConv2D operation
DeConv2DDerivative	DeConv2DDerivative operation
DepthToSpace	Inverse operation to SpaceToDepth.
DepthwiseConv2D	Depthwise Conv2D operation
FullConv3D	FullConv3D operation
FullConv3DDerivative	FullConv3DDerivative operation
Im2col	Im2col operation
LegacyPooling2D	Deprecated Note: This operation will be removed in a future release
LocalResponseNormalization	LocalResponseNormalization operation
LocalResponseNormalizationDerivative	LocalResponseNormalizationDerivative operation
MaxPooling2D	Max Pooling2D operation
Pooling2D	Pooling2D operation
Pooling2DDerivative	Pooling2DDerivative operation
Pooling3D	Pooling3D operation
Pooling3DDerivative	Pooling3DDerivative operation
SConv2D	Separable convolution 2D operation
SConv2DDerivative	SConv2DDerivative operation
SpaceToDepth	This operation takes 4D array in, in either NCHW or NHWC format, and moves data from spatial dimensions (HW) to channels (C) for given blockSize
Upsampling	Upsampling operation
UpsamplingDerivative	UpsamplingDerivative operation

Enum Summary

Enum	Description
AvgPooling2D.Pooling2DType
LegacyPooling2D.Pooling2DType
Pooling2D.Divisor	Divisor mode for average pooling only.
Pooling2D.Pooling2DType
Pooling3D.Pooling3DType