TransposedConv1d
class TransposedConv1d<T : DType, V>(val inChannels: Int, val outChannels: Int, val kernelSize: Int, val stride: Int = 1, val padding: Int = 0, val outputPadding: Int = 0, val dilation: Int = 1, val groups: Int = 1, val bias: Boolean = true, val name: String = "TransposedConv1d", initWeights: Tensor<T, V>, initBias: Tensor<T, V>? = null, val trainable: Boolean = true) : Module<T, V> , ModuleParameters<T, V> (source)
1D Transposed Convolutional layer (also known as fractionally-strided convolution).
This layer is commonly used for upsampling in generative models, audio synthesis (e.g. BigVGAN, Voxtral codec), and decoder architectures.
Parameters
inChannels
Number of input channels
outChannels
Number of output channels
kernelSize
Size of the convolving kernel
stride
Stride of the convolution (default: 1)
padding
Padding added to both sides of the input (default: 0)
outputPadding
Additional size added to one side of the output (default: 0)
dilation
Spacing between kernel elements (default: 1)
groups
Number of blocked connections from input channels to output channels (default: 1)
bias
Whether to add a learnable bias to the output (default: true)
name
Name of the module
initWeights
Initial weights tensor
initBias
Initial bias tensor (if bias is true)
Constructors
Link copied to clipboard
constructor(inChannels: Int, outChannels: Int, kernelSize: Int, stride: Int = 1, padding: Int = 0, outputPadding: Int = 0, dilation: Int = 1, groups: Int = 1, bias: Boolean = true, name: String = "TransposedConv1d", initWeights: Tensor<T, V>, initBias: Tensor<T, V>? = null, trainable: Boolean = true)