| from typing import Optional | |
| import torch | |
| def one_hot( | |
| labels: torch.Tensor, | |
| num_classes: int, | |
| device: Optional[torch.device] = None, | |
| dtype: Optional[torch.dtype] = None, | |
| eps: float = 1e-6, | |
| ) -> torch.Tensor: | |
| r"""Convert an integer label x-D tensor to a one-hot (x+1)-D tensor. | |
| Args: | |
| labels: tensor with labels of shape :math:`(N, *)`, where N is batch size. | |
| Each value is an integer representing correct classification. | |
| num_classes: number of classes in labels. | |
| device: the desired device of returned tensor. | |
| dtype: the desired data type of returned tensor. | |
| Returns: | |
| the labels in one hot tensor of shape :math:`(N, C, *)`, | |
| Examples: | |
| >>> labels = torch.LongTensor([[[0, 1], [2, 0]]]) | |
| >>> one_hot(labels, num_classes=3) | |
| tensor([[[[1.0000e+00, 1.0000e-06], | |
| [1.0000e-06, 1.0000e+00]], | |
| <BLANKLINE> | |
| [[1.0000e-06, 1.0000e+00], | |
| [1.0000e-06, 1.0000e-06]], | |
| <BLANKLINE> | |
| [[1.0000e-06, 1.0000e-06], | |
| [1.0000e+00, 1.0000e-06]]]]) | |
| """ | |
| if not isinstance(labels, torch.Tensor): | |
| raise TypeError(f"Input labels type is not a torch.Tensor. Got {type(labels)}") | |
| if not labels.dtype == torch.int64: | |
| raise ValueError(f"labels must be of the same dtype torch.int64. Got: {labels.dtype}") | |
| if num_classes < 1: | |
| raise ValueError("The number of classes must be bigger than one." " Got: {}".format(num_classes)) | |
| shape = labels.shape | |
| one_hot = torch.zeros((shape[0], num_classes) + shape[1:], device=device, dtype=dtype) | |
| return one_hot.scatter_(1, labels.unsqueeze(1), 1.0) + eps | |