Advertisement

Pytorch RuntimeError: Expected 4-dimensional input for 4-dimensional weight [512, 512, 3, 3], but go

阅读量:
复制代码
    RuntimeError: Expected 4-dimensional input for 4-dimensional weight [512, 512, 3, 3], but got 2-dimensional input of size [4, 512] instead
    
    
    
    bash

conv2d卷积层的输入尺寸存在不匹配问题,系统期望接收的输入格式为[512, 512, 3, 3],但当前实际接收到的输入维度为[4, 512]。
临时应对措施为:将二维张量扩展为四维张量以满足输入要求。

复制代码
    someTensor = someTensor.unsqueeze(2).unsqueeze(3)
    
    
    python

具体表现如下:

复制代码
    >>> a.shape
    torch.Size([2, 2])
    >>> a.unsqueeze(2).shape
    torch.Size([2, 2, 1])
    >>> a.unsqueeze(2).unsqueeze(3).shape
    torch.Size([2, 2, 1, 1])
    
    
    bash

https://stackoverflow.com/quest

全部评论 (0)

还没有任何评论哟~