FoundationVision / OmniTokenizer

[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.
https://www.wangjunke.info/OmniTokenizer/
MIT License
263 stars 7 forks source link

cuda segment fault in PEG->forward->self.dsconv(x) #10

Closed dreamofuture closed 4 months ago

dreamofuture commented 4 months ago

hello, encountered this problem when run vqgan.encode(img) in 4090, solved by self.dsconv(x.contiguous())