xiaodan

Results 5 comments of xiaodan

If we test on custom video, it seems that the information like attention_relationship and bboxes are required?

> > If we test on custom video, it seems that the information like attention_relationship and bboxes are required? > > Why? The attention relationships should be predicted and the...

Hi @JingweiJ , looking forward to the baseline implementations. Thank you very much!

Met the same problem. Please help! My flax version is 0.5.3.