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

TORCH.TENSOR.SCATTER_

Tensor.scatter_(dimindexsrcreduce=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().

selfindex 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(), 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

【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

torch.Tensor.scatter_ — PyTorch 1.13 documentation

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值