csdwren / SelfDeblur

Neural Blind Deconvolution Using Deep Priors (CVPR 2020)
336 stars 68 forks source link

RuntimeError: set_storage_offset is not allowed on a Tensor created from .data or .detach(). #11

Open bixiwen opened 4 years ago

bixiwen commented 4 years ago

Hi,when I run selfdeblur_levin.py,I have the error: im1_kernel1_img Traceback (most recent call last): File "selfdeblur_levin.py", line 101, in net_inputkernel.squeeze() RuntimeError: set_storage_offset is not allowed on a Tensor created from .data or .detach(). If your intent is to change the metadata of a Tensor (such as sizes / strides / storage / storage_offset) without autograd tracking the change, remove the .data / .detach() call and wrap the change in a with torch.no_grad(): block. For example, change: x.data.set_(y) to: with torch.nograd(): x.set(y)

csdwren commented 4 years ago

I think you are using higher version Pytorch. You can try to delete “.detach()” in variables "net_input" and "net_input_kernel"

bixiwen commented 4 years ago

I think you are using higher version Pytorch. You can try to delete “.detach()” in variables "net_input" and "net_input_kernel"

Thank you so much!