how to

errors

Jun 8, 2025
langspythonpytorch
1 Minutes
46 Words
  • [25.6.7]
    • RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same or input should be a MKLDNN tensor and weight is a dense tensor
    • [ok, problem is] Tensor 不在一个设备上.
    1
    net = BasicUNet(in_channels=1, out_channels=1).to(<gpu>)
    2
    x = torch.randn(8, 1, 28, 28)
    3
    net(x)
unit2-01_finetuning_and_guidance
修改历史上的 commit message
Article title：errors
Article author：Julyfun
Release time：Jun 8, 2025
Copyright 2025
Sitemap