tiandiao123 commented on issue #8057:
URL: https://github.com/apache/tvm/issues/8057#issuecomment-858216535
> It is possible that relay and PT have different deform conv 2d results. I
had put up a PR #7397 which fixed this for PT 1.6 . It's possible they changed
something for later
tiandiao123 commented on issue #8057:
URL: https://github.com/apache/tvm/issues/8057#issuecomment-857497838
If you guys can check, I found that the deformable conv2d ops of pytorch and
the deformable conv2d op of relay api have different result :
tiandiao123 commented on issue #8057:
URL: https://github.com/apache/tvm/issues/8057#issuecomment-857496229
> thanks for that tip @masahi, I will start researching and trying to solve
the problem from there
Hi, does it have some progress? I have the same issue here.
--
This is