Uses of Class
org.nd4j.enums.DataFormat
-
Packages that use DataFormat Package Description org.nd4j.autodiff.samediff.ops org.nd4j.enums org.nd4j.linalg.api.ops.impl.layers.convolution org.nd4j.linalg.factory.ops -
-
Uses of DataFormat in org.nd4j.autodiff.samediff.ops
Methods in org.nd4j.autodiff.samediff.ops with parameters of type DataFormat Modifier and Type Method Description SDVariableSDCNN. depthToSpace(String name, SDVariable x, int blockSize, DataFormat dataFormat)Convolution 2d layer batch to space operation on 4d input.
Reduces input channels dimension by rearranging data into a larger spatial dimensions
Example: if input has shape [mb, 8, 2, 2] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2]
= [mb, 2, 4, 4]SDVariableSDCNN. depthToSpace(SDVariable x, int blockSize, DataFormat dataFormat)Convolution 2d layer batch to space operation on 4d input.
Reduces input channels dimension by rearranging data into a larger spatial dimensions
Example: if input has shape [mb, 8, 2, 2] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2]
= [mb, 2, 4, 4]SDVariableSDCNN. spaceToDepth(String name, SDVariable x, int blockSize, DataFormat dataFormat)Convolution 2d layer space to depth operation on 4d input.
Increases input channels (reduced spatial dimensions) by rearranging data into a larger channels dimension
Example: if input has shape [mb, 2, 4, 4] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2]
= [mb, 2, 4, 4]SDVariableSDCNN. spaceToDepth(SDVariable x, int blockSize, DataFormat dataFormat)Convolution 2d layer space to depth operation on 4d input.
Increases input channels (reduced spatial dimensions) by rearranging data into a larger channels dimension
Example: if input has shape [mb, 2, 4, 4] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2]
= [mb, 2, 4, 4] -
Uses of DataFormat in org.nd4j.enums
Methods in org.nd4j.enums that return DataFormat Modifier and Type Method Description static DataFormatDataFormat. valueOf(String name)Returns the enum constant of this type with the specified name.static DataFormat[]DataFormat. values()Returns an array containing the constants of this enum type, in the order they are declared. -
Uses of DataFormat in org.nd4j.linalg.api.ops.impl.layers.convolution
Constructors in org.nd4j.linalg.api.ops.impl.layers.convolution with parameters of type DataFormat Constructor Description DepthToSpace(SameDiff sameDiff, SDVariable[] args, int blockSize, DataFormat dataFormat)DepthToSpace(SameDiff sameDiff, SDVariable args, int blockSize, DataFormat dataFormat)DepthToSpace(INDArray in, int blockSize, DataFormat dataFormat)DepthToSpace(INDArray in, INDArray out, int blockSize, DataFormat dataFormat)SpaceToDepth(SameDiff sameDiff, SDVariable[] args, int blockSize, DataFormat dataFormat)SpaceToDepth(SameDiff sameDiff, SDVariable x, int blockSize, DataFormat dataFormat)SpaceToDepth(INDArray x, int blockSize, DataFormat dataFormat)SpaceToDepth(INDArray in, INDArray out, int blockSize, DataFormat dataFormat) -
Uses of DataFormat in org.nd4j.linalg.factory.ops
Methods in org.nd4j.linalg.factory.ops with parameters of type DataFormat Modifier and Type Method Description INDArrayNDCNN. depthToSpace(INDArray x, int blockSize, DataFormat dataFormat)Convolution 2d layer batch to space operation on 4d input.
Reduces input channels dimension by rearranging data into a larger spatial dimensions
Example: if input has shape [mb, 8, 2, 2] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2]
= [mb, 2, 4, 4]INDArrayNDCNN. spaceToDepth(INDArray x, int blockSize, DataFormat dataFormat)Convolution 2d layer space to depth operation on 4d input.
Increases input channels (reduced spatial dimensions) by rearranging data into a larger channels dimension
Example: if input has shape [mb, 2, 4, 4] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2]
= [mb, 2, 4, 4]
-