search

OpenGVLab / VideoMamba

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding
https://arxiv.org/abs/2403.06977
Apache License 2.0
849 stars 60 forks source link

Masked Pretraining section #54

Open Sine7812 opened 6 months ago

Sine7812 commented 6 months ago

In the Masked Pretraining section, there seems to be an issue with the way the CLIP model is loaded. In the extract.ipynb notebook, the code model, _ = clip.load("ViT-B/16", device='cpu') is used, but the CLIP code repository does not have a load module, and the import import clip.clip as clip does not seem to be the correct way to do it.

Sine7812 commented 6 months ago

屏幕截图 2024-05-12 205837 我知道了，应该先安装clip,链接是https://github.com/openai/CLIP/blob/main/notebooks/Interacting_with_CLIP.ipynb，然后运行就行了，如果在jupter里面运行还是出错，可以直接在命令行运行

Andy1621 commented 6 months ago

Good try!