Honey Gupta
Results
3
comments of
Honey Gupta
For me, it gave this error if I used any tensorflow version other than 1.2.
So that was a factor we added because of the pixel range of the depth maps in the Berman's dataset. AFAIR, the depth maps in the dataset are 16 bit...
> And you set the nan in gt to 0, did you do this for masking these points when calculating the error? Yes, we only consider the non-nan pixels for...