How to understand the "training for multiple flow" and the "div_flow" about flownet2-pytorch

[ClementPinard]

div_flow is used for 2 reasons :

• Training is deemed more stable for low output target values.
• it was used by initial caffe code, and thus it makes this training compatible with a pretrained model from caffe.

[JiamingSuen]

Just provide some information here, for issue1 MultiScale loss is accepting a tuple of flow predictions which should be the returned flows you mentioned. The ground truth scaling is proceeded here with AvgPool2d.
For issue2 it's still not clear to me but I found this explanation in @ClementPinard 's original implementation. Maybe one of the authors would explain.

Hope this will help.

[PkuRainBow]

I guess that the "div_flow" is in fact to controll the previously learned flow as the main component and keep the later flow as the residual. So the "div_flow" must be larger than 1, how to choose the value of "div_flow" is a hyperparamter choice. Do I get it right?

[fitsumreda]

I will close this, as sufficient explanation was given by @ClementPinard.