espnet2.legacy.nets.pytorch_backend.wavenet.UpSampling

source

class espnet2.legacy.nets.pytorch_backend.wavenet.UpSampling(upsampling_factor, bias=True)

Bases: Module

Upsampling layer with deconvolution.

• Parameters:upsampling_factor (int) – Upsampling factor.

Initialize Upsampling class.

forward(x)

Calculate forward propagation.

• Parameters:x (Tensor) – Input tensor with the shape (B, C, T)
• Returns: Tensor with the shape (B, C, T’) where T’ = T * upsampling_factor.
• Return type: Tensor