Pytorch：使用scatter()、scatter_()将Label变成one-hot编码

梦里梦外; 2023-09-25 14:33 46阅读 0赞

## TORCH.TENSOR.SCATTER\_ ##

Tensor.scatter\_(*dim*, *index*, *src*, *reduce=None*) → [Tensor][]

Writes all values from the tensor `src` into `self` at the indices specified in the `index` tensor. For each value in `src`, its output index is specified by its index in `src` for `dimension != dim` and by the corresponding value in `index` for `dimension = dim`.

For a 3-D tensor, `self` is updated as:

self[index[i][j][k]][j][k] = src[i][j][k]  # if dim == 0
    self[i][index[i][j][k]][k] = src[i][j][k]  # if dim == 1
    self[i][j][index[i][j][k]] = src[i][j][k]  # if dim == 2

This is the reverse operation of the manner described in [gather()][gather].

`self`, `index` and `src` (if it is a Tensor) should all have the same number of dimensions. It is also required that `index.size(d) <= src.size(d)` for all dimensions `d`, and that `index.size(d) <= self.size(d)` for all dimensions `d != dim`. Note that `index` and `src` do not broadcast.

Moreover, as for [gather()][gather], the values of `index` must be between `0` and `self.size(dim) - 1` inclusive.

[Pytorch中，将label变成one hot编码的两种方式\_咆哮的阿杰的博客-CSDN博客\_label onehot编码][Pytorch_label_one hot_-CSDN_label onehot]

[【函数小trick】torch中scatter()、scatter\_()详解（多标签one-hot向量生成）\_诸葛灬孔暗的博客-CSDN博客\_torch生成onehot][trick_torch_scatter_scatter_one-hot_-CSDN_torch_onehot]

[torch.Tensor.scatter\_ — PyTorch 1.13 documentation][torch.Tensor.scatter_ _ PyTorch 1.13 documentation]

[Tensor]: https://pytorch.org/docs/stable/tensors.html#torch.Tensor
[gather]: https://pytorch.org/docs/stable/generated/torch.Tensor.gather.html#torch.Tensor.gather
[Pytorch_label_one hot_-CSDN_label onehot]: https://blog.csdn.net/qq_34914551/article/details/88700334
[trick_torch_scatter_scatter_one-hot_-CSDN_torch_onehot]: https://blog.csdn.net/qq_39383591/article/details/118481540
[torch.Tensor.scatter_ _ PyTorch 1.13 documentation]: https://pytorch.org/docs/stable/generated/torch.Tensor.scatter_.html#torch.Tensor.scatter_