Image size for running demo_8x.py

ltkong218 / IFRNet

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation (CVPR 2022)

MIT License

276 stars 23 forks source link

Image size for running demo_8x.py #17

Open abhishri-medewar opened 2 years ago

abhishri-medewar commented 2 years ago

What are the image sizes that I can use to run demo_8x.py ? I am trying to run using 1920 X 1080 image size but I am getting an error.

ltkong218 commented 2 years ago

The input size of IFRNet should be divided by 16. You can first pad the input frames, and then unpad the output frame. You can refer to benchmarks/SNU_FILM.py. Thanks.