Closed xingbo-jiang closed 2 years ago
When it is zero, it doesn't matter when you warp it or not. It is still a zero feature. Therefore, we skip the warping to save computational cost.
Thanks for your reply and i like your work very much, but i still have a question. In this way, computational cost is saved, however, the feature of adjacent frames is not transmitted to the feat-prop,which seems inconsistent with the paper. By the way, is the saving of computational cost substantial?
At i=0
, there is no neighbouring feature, and therefore you can directly set feat_prop
to zero. For i>0
, we need to use cond_n1
and cond_n2
to align the neighboring feature
OHHH,i get it. Sorry, I was sloppy when I looked at the code😂. Thank you very much🤞.
why the cond_n1 is the out of flow_wrap(feat_prop, flow_n1.permute(0, 2, 3, 1)) while feat_prop is zeros? why not flow_wrap(feat_n1,flow_n1.permute(0, 2, 3, 1) and feat_n1 = feats[module_name][-1]