Does SparseConv3d & SubMConv3d always produce exactly the same outputs?

[zodiac000]

I found out by given the same set of inputs always receiving slightly different outputs. The diff is roughly about 10^-5. This is awkward. Is there any randomness involved in the implementation of 3DConv in spconv2.X or spconv1.X? If so, is there any way to avoid the randomness occuring.

[jisoo0-0]

same here. .. Did you solved the problem..??

[harrydobbs]

Same here - did either of you find a solution?