search

michaildoukas / head2head

PyTorch implementation for Head2Head and Head2Head++. It can be used to fully transfer the head pose, facial expression and eye movements from a source video to a target identity.
MIT License
310 stars 44 forks source link

pytorch version error #10

Closed visonpon closed 3 years ago

visonpon commented 3 years ago

@michaildoukas, thanks for your great work, and when I try to use it, I got some PyTorch version compatible errors.

since the flownet_pytorch relies on pytorch0.4.1 and torchvision0.2.2, but this work relies on pytorch1.4 and torchvison0.5. when the flownet_pytorch compile success, the facenet_pytorch raise an error no module named torchvison.ops because the torchvison-0.2.2 is low, but when I change the PyTorch to 1.4 and torchvision to 0.5, I got an error Undefined symbol: _ZN2at5ErrorC1ENS_14SourceLocationESs that in the flownet_pytorch project it seems to have to use torch0.4.1...

so these two frameworks conflicting with each other, hope you can help, thanks~

cyrala commented 2 years ago

@michaildoukas, thanks for your great work, and when I try to use it, I got some PyTorch version compatible errors.

since the flownet_pytorch relies on pytorch0.4.1 and torchvision0.2.2, but this work relies on pytorch1.4 and torchvison0.5. when the flownet_pytorch compile success, the facenet_pytorch raise an error no module named torchvison.ops because the torchvison-0.2.2 is low, but when I change the PyTorch to 1.4 and torchvision to 0.5, I got an error Undefined symbol: _ZN2at5ErrorC1ENS_14SourceLocationESs that in the flownet_pytorch project it seems to have to use torch0.4.1...

so these two frameworks conflicting with each other, hope you can help, thanks~

Hi, I also encounterd this problem, have you solved it?