Open AshinCarlXiao opened 6 years ago
Regarding point 3, it seems also that the loss function in the code is different from what's in the paper. There may be other differences; I haven't gone into it in detail yet.
@AshinCarlXiao @sesse The big problem is the work use the tanh function as activate function in the last layer. It is not reasonable. The flow value will be restricted in [-1.0, 1.0].
This repository only contains the basic network setup for deep voxel flow. Skip connections and multi-scale architecture are not included here. For more updates, please refer to our newly released pytorch-voxel-flow: https://github.com/lxx1991/pytorch-voxel-flow .
Note that the voxel flow representation implemented in the network is actually normalized flow ranging from [-1, 1]. When applied to real frames, they have been re-scaled to the full size as: flow = height (or width) * flow. Please refer to the code ("utils/geo_layer_utils.py") for more details.
I am trying to reproduce your work lately, and I got three questions.
very looking forward to your reply, thanks a lot!!!