vak.nn.functional

Functions

one_hot(labels, num_classes[, device, ...])

Converts an integer label x-D tensor to a one-hot (x+1)-D tensor. :param labels: tensor with labels of shape \((N, *)\), where N is batch size. Each value is an integer representing correct classification. :type labels: torch.Tensor :param num_classes: number of classes in labels. :type num_classes: int :param device: the desired device of returned tensor. Default: if None, defaults to device of labels. :type device: Optional[torch.device] :param dtype: the desired data type of returned tensor. Default: if None, infers data type from values. :type dtype: Optional[torch.dtype].