search

harlanhong / CVPR2022-DaGAN

Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation
https://harlanhong.github.io/publications/dagan.html
Other
957 stars 125 forks source link

CUDA error: operation not supported when calling `cusparseCreate(handle)` #82

Open ZanderInteractiveMedia opened 5 months ago

ZanderInteractiveMedia commented 5 months ago

python demo.py --config config/vox-256.yaml --driving_video media/video.mp4 --source_image media/image.jpg --checkpoint checkpoint/DaGAN_vox_adv_256.pth.tar --relative --adapt_scale - -kp_num 15 --generator DepthAwareGenerator 0%| | 0/48 [00:01<?, ?it/s] Traceback (most recent call last): File "demo.py", line 205, in <module> sources, drivings, predictions,depth_gray = make_animation(source_image, driving_video, generator, kp_detector, relative=opt.relative, adapt_movement_scale=opt.adapt_scale, cpu=opt.cpu) File "demo.py", line 99, in make_animation use_relative_jacobian=relative, adapt_movement_scale=adapt_movement_scale) File "D:\TalkingHead(DaGAN)\CVPR2022-DaGAN\animate.py", line 33, in normalize_kp jacobian_diff = torch.matmul(kp_driving['jacobian'], torch.inverse(kp_driving_initial['jacobian'])) RuntimeError: CUDA error: operation not supported when callingcusparseCreate(handle)`

what does this mean and what can I do ?