Contents

init(sequenceLength:featureChannelCount:batchSize:)

Creates a tensor without data, with the sequence length, number of feature channels, and batch size you specify.

Declaration

convenience init(sequenceLength: Int, featureChannelCount: Int, batchSize: Int)

Parameters

  • sequenceLength:

    The length of sequences stored in the tensor.

  • featureChannelCount:

    The number of feature channels.

  • batchSize:

    The tensor batch size.

Discussion

The tensor data type is MLCDataType.float32. This tensor is typically used by a recurrent layer.

See Also

Creating Tensors by Specifying Sequence Lengths