search

ArrowLuo / CLIP4Clip

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"
https://arxiv.org/abs/2104.08860
MIT License
879 stars 123 forks source link

train on DiDeMo #87

Open qjyyyy opened 1 year ago

qjyyyy commented 1 year ago

Thanks for sharing your wonderful work!

When I train on DiDeMo dataset, the following information appears on the terminal more than once. 139ae0410327e9b89ba27ca5d1d6cfe

But the model training was not interrupted. The model could be trained and tested normally. I ran according to the training parameters on DiDeMo dataset you provided, but changed the batch size. I want to know whether you have encountered the same situation, and whether it will affect the model results? I searched the Internet for solutions, but I could hardly find them.

ArrowLuo commented 1 year ago

Hi @qjyyyy, I suppose that it is a problem with video decoding. But I am unsure of the reason, and a suggestion is to scan all videos via rawvideo_util.py#L25 offline and print the video name to see which one occurs such an issue. I am also not sure about the effect on the results. Best~