torchaudio (version 0.3.1)

model_resblock: ResBlock

Description

ResNet block based on "Deep Residual Learning for Image Recognition". Pass the input through the ResBlock layer. The paper link is https://arxiv.org/pdf/1512.03385.pdf.

Usage

model_resblock(n_freq = 128)

Value

Tensor shape: (n_batch, n_freq, n_time)

Arguments

n_freq

the number of bins in a spectrogram. (Default: 128)

Details

forward param: specgram (Tensor): the input sequence to the ResBlock layer (n_batch, n_freq, n_time).

Examples

if(torch::torch_is_installed()) {
resblock = model_resblock()
input = torch::torch_rand(10, 128, 512)  # a random spectrogram
output = resblock(input)  # shape: (10, 128, 512)
}