Xinyang Han

icon company UC Berkeley icon location Berkeley icon location Unsupervised Learning at Scale

Results 4 comments of Xinyang Han

The results seem less than ideal

Yes!!! Indeed!!! Same for me!!! The reconstruction and editing ability has a gap with the exhibited result in paper!!!!!!!!!!

The experiment using FACS to evaluate the 3D consistency

Thanks a lot for your instant reply! However, since I do not have a windows system with nvidia GPU. May I ask if there are other alternatives that have similar...

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper__index_select)`

same problem

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper__index_select)`

@xzdong-2019, may I ask how did you solve that? I mean where should us add gpus=1?