init(width:height:featureChannelCount:batchSize:dataType:)
Creates a tensor descriptor with the width and height, number of feature channels, batch size, and data type you specify.
Declaration
convenience init?(width: Int, height: Int, featureChannelCount: Int, batchSize: Int, dataType: MLCDataType)Parameters
- width:
The tensor width.
- height:
The tensor height.
- featureChannelCount:
The number of feature channels.
- batchSize:
The tensor batch size.
- dataType:
The tensor data type.
Discussion
This initializer provides a convenient way for you to configure NCHW tensors used by convolutional layers.
See Also
Creating Tensor Descriptors
init(shape:dataType:)init(shape:sequenceLengths:sortedSequences:dataType:)init(width:height:featureChannelCount:batchSize:)init(convolutionWeightsWithInputFeatureChannelCount:outputFeatureChannelCount:dataType:)init(convolutionWeightsWithWidth:height:inputFeatureChannelCount:outputFeatureChannelCount:dataType:)init(convolutionBiasesWithFeatureChannelCount:dataType:)maxTensorDimensions