New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

of extraction #2

Open

st-fei opened this issue Apr 2, 2024 · 1 comment

st-fei commented Apr 2, 2024

作者您好，我注意到您的工作中使用了光流模态，我尝试从长视频中提取光流，但是其耗时较长，存储成本较高。想请问您是否对长视频作了特殊的处理，谢谢 -v-

Collaborator

patrick-tssn commented Apr 26, 2024

抱歉现在才注意到这个issue，我们对视频限制了最大帧数，参考 eval/utils/builder_utils.py 中的 get_frame() 函数；此外，为了加速训练，我们对视频压缩到2fps，压缩工具可以参考：https://github.com/jayleicn/singularity/blob/main/preprocess/compress.py

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment