Jintao Lin
Jintao Lin
@17Skye17 It seems that the author will remove '-' and '_' chars when a video id starts with these two. And @sallymmx Could you please provide the validation videos ?
> 您好，我是王蒙蒙，您的邮件我已收到，并及时回复。 谢谢，请问您能提供这些 video_id 的视频吗，可以发到 [email protected] ``` NtUqv_6vdU 3MhOA-vSO8 JwMoMeZ_v8 LrBC1_yf04 c96bD-9fHs blq_c14hGQ bVVs-nntQ sSTHZHHp-c WI7e5-wURs iox_MbwxNg IAo-mNduUk 2L8B_meOLE wdnasc-fCg NMaC-IGv_Q OoJW-OeFtw jR-X0LqwpY c-YbuFrXbI H-Ww0gGDWU Xfmjzt_n24 I3_52Xh7oU UqI-TBQRgg RlFMUo-JE Ykfa-4qx0...
It now supports to output video format and gif format in `demo.py`.
> There are many trained models in Model Zoo, while all of them are just used to test the performance of the proposed works. Do you plan to make them...
> Could you please support X3D Here is the X3D config files. https://github.com/open-mmlab/mmaction2/tree/master/configs/recognition/x3d
We haven't reimplemented some SOTA methods owing to the lack of computation resources, especially some methods using additional data pertaining. But I think we can add them in the future...
For convenience, you can set `args` as a global variant.
I rerun it successfully. Based on my wild guess, it may cause by the version of Python
Could u try to use `torch.cuda.synchronize()` to calc the inference time ?
Actually, I don't know what you mean. We also provide OpenCV API in `OpenCVDecord` to decord video In the fly.