08.04.2018 · when import torch, an AttributeError is raised saying `` 'module' object has no attribute 'cuda' " #6412 Closed zengxianyu opened this issue on Apr 8, 2018 · 7 comments zengxianyu commented on Apr 8, 2018 • edited A script to reproduce the bug. Please try to provide as minimal of a test case as possible:
25.05.2020 · It seems the .grad attribute wasn’t populated so you might have accidentally detached some tensors from the computation graph. Could you check the .grad attribute of other layers and make sure you see valid values? Also, don’t use the .data attribute, as it may yield unwanted side effects.. Alternatively to your current workflow you could also use hooks via …
14.11.2019 · Disable autograd while you update your weights to avoid the second one. Here is the new code update: for i in range (epochs): predict = torch.mm (feature, weight) + bias.item () loss = torch.sum (predict - label, dim=0) loss.backward () # Disable the autograd with torch.no_grad (): # Inplace changes weight.sub_ (weight.grad*lr) bias.sub_ (bias ...
21.05.2021 · The latest version of pytorch implements all fast fourier functions in the module torch.fft, apparently piq rely on an older version of pytorch, so if you want to run piq consider downgrading your pytorch version, for example: pip3 install torch==1.7.1 torchvision==0.8.2. Share. Improve this answer. Follow this answer to receive notifications.