Cannot input a tensor of dimension other than 0 as a scalar argument

最新推荐文章于 2022-08-29 13:54:25 发布

AI算法网奇

最新推荐文章于 2022-08-29 13:54:25 发布

阅读量3.2k

点赞数

分类专栏： c++入门宝典 pytorch知识宝典

本文链接：https://blog.csdn.net/jacke121/article/details/93760076

版权

pytorch知识宝典同时被 2 个专栏收录

500 篇文章 227 订阅 ¥29.90 ¥99.00

订阅专栏

超级会员免费看

c++入门宝典

358 篇文章 123 订阅 ¥29.90 ¥99.00

订阅专栏

超级会员免费看

在编程过程中遇到一个错误，当尝试将一个非零维度的张量作为标量参数时，系统抛出'Cannot input a tensor of dimension other than 0 as a scalar argument'的错误。具体出现在代码行`channels_per_group = num_channels // groups`，此处需要确保输入是0维张量。

摘要由CSDN通过智能技术生成

Cannot input a tensor of dimension other than 0 as a scalar argument

错误代码：

channels_per_group = num_channels // groups

 @torch.jit.script_method
    def channel_shuffle(self, x, groups):
        batchsize, num_channels, height, width = x.size()
        # assert (num_channels % groups == 0)
        channels_per_group = num_channels // groups
        # reshape
        x = x.view(batchsize, groups, channels_per_group, height, width)

        # transpose
        # - contiguous() required if transpose() is used before view().
        #   See https://github.com/pytorch/pytorch/issues/764
        x = torch.transpose(x, 1, 2).contiguous()

        # flatten
        x = x.view(batchsize, -1, height, width)

        return x