bayesian_inception_time#

torch_uncertainty.models.bayesian_inception_time(in_channels, num_classes, num_samples=16, kernel_size=40, embed_dim=32, num_blocks=6, dropout=0.0, residual=True)[source]#

Bayesian InceptionTime.

Parameters:

  • in_channels (int) – Number of input channels.

  • num_classes (int) – Number of output classes.

  • num_samples (int) – Number of samples for stochastic modeling. Defaults to 16.

  • kernel_size (int) – Size of the convolutional kernels. Defaults to 40.

  • embed_dim (int) – Dimension of the embedding. Defaults to 32.

  • num_blocks (int) – Number of inception blocks. Defaults to 6.

  • dropout (float) – Dropout rate. Defaults to 0.0.

  • residual (bool) – Whether to use residual connections. Defaults to True.

Returns:

A stochastic InceptionTime model.

Return type:

StochasticModel