A re-train normal CNN on scaled data beats deform-conv. about pytorch-deform-conv HOT 3 OPEN

@Kaidy-Boom I meet the same problem,I think the reason is that the mnist is too easy for them to learn.I delete the first two Deformable layers and only keep the last one seems to have a better result.

from pytorch-deform-conv.

@Kaidy-Boom @wushuang01 Thanks for your report, indeed that's not a good demo of the effectiveness. To clarify, my implementation is just a port of the tensorflow version by Felix Lau as mentioned in README, I discussed with him briefly in the past about a similar question, and I did not have time to do more for that. For a complete prove of the effectiveness, I think would be better to check the original paper.

from pytorch-deform-conv.

@oeway Thanks for your reply.appreciate for your work which is helpful for me.

from pytorch-deform-conv.