nofreewill42
nofreewill42
Wouldn't it make sense to not just train on two different transformations of the same image, but on transformations of two close enough frames of the same video? For faster...
Could also remove lines 34-35 and modify line 21 so that "mkdir" has argument "parents=True", but didn't check if that makes it slower or not.
No usage of argument p in resizes and resize_img functions.
In the cloned repo, with Paligon built that comes with the repo I build the plotTrajectory.cpp as follows: ``` cd slambook2/ch3/examples mkdir build cd build cmake .. make cd ../.....