Shenglong Zhou

> @tsenst Hi, I also have this problem. do you find the reason and the corresponding solution? Hi~ Have you solved the problems ?

> @xianshunw @Blcony Hi, I try to fine-tune or train on MPISintel, but the loss and epe are all ''nan' > like this > `2019-09-17 00:36:04 Iter 1000 [Train]: loss=nan,...

@philferriere Thank you for your discussion. Is there any updated results using the correct fuction(i.e. query_points_on_grid = batched_grid + flow)? I noticed that the code in master branch is still...

> the use of dense_image_warp function is wrong. In line 194 of file core_warp.py, you use `query_points_on_grid = batched_grid - flow` but what this line does is a forward warp....