search

sniklaus / 3d-ken-burns

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch
Other
1.52k stars 225 forks source link

segmentation fault . #19

Closed lulu1315 closed 4 years ago

lulu1315 commented 4 years ago

running on KDE Neon (Ubuntu 18.04) NVIDIA Corporation GM200 [GeForce GTX TITAN X] (rev a1) Cuda compilation tools, release 10.2, V10.2.89 Cudnn 7.6.5 Python 3.6.9 torch 1.5.0a0+90a259e (compiled from source) torchvision 0.6.0a0+28b7f8a (compiled from source)

command : python3 autozoom.py --in ./images/doublestrike.jpg --out ./autozoom.mp4 i've got a Segmentation fault when arriving on this line in common.py in process_load() tensorDisparity = disparity_estimation(tensorImage)

thanks for your help. luc

sniklaus commented 4 years ago

It seems like you are using a pre-release / alpha version of PyTorch and TorchVision. Have you tried one of the official releases?

lulu1315 commented 4 years ago

hello and thank you.it works now.

switched to cuda 10.1 and corresponding Cudnn torch==1.4.0 torchvision==0.5.0 cupy-cuda101==7.1.1

thank you very much for the code. luc

sniklaus commented 4 years ago

Thanks for letting me know, I am happy to hear that!