hzwer

I currently have many other experiments to improve visual effects. Improving efficiency is currently not a high priority work. Is there any data to illustrate the speedup of RIFE at...

OK. At present, it seems that there is indeed a need to reduce the memory overhead, and I can design some new models.

I have no ideas. Anyone can answer this question？:)

这个得寻求一些软件帮助，据我所知 SVFI 有这个功能。

For model inference, I have not implemented the relevant code because most users only have one GPU. For model training, the default is 4 GPUs: https://github.com/hzwer/arXiv2020-RIFE#training-and-reproduction

1. 可以把 refinenet 去掉，2. 可以在 inference 的时候把 scale 调成 0.5

I'm not sure the detailed of this error. I recommend to use some GUI software, such as https://github.com/n00mkrad/flowframes.

I add a simple interface, I recommend to use RIFEm parameters => https://github.com/megvii-research/ECCV2022-RIFE#evaluation And I wrote an example, not sure how it works ``` import torch from torch.nn import functional...

Yes, I think you get it. I may add this issue to our README because it seems to be a useful function.

Hello, the v4.0 model seems to be abnormal for the scale > 2. I don't know the specific reason.