Question about the benchmark_datasets

mikacuy / pointnetvlad

PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition, CVPR 2018

MIT License

351 stars 72 forks source link

Question about the benchmark_datasets #7

Closed ahandsomeperson closed 5 years ago

ahandsomeperson commented 5 years ago

Hi, thanks for your great job! But I am trying to visualize your submaps, and the following picture is from one of the .bin file However, the max value is up to 10^38. I have no idea what is the visualization result represent for. Is there something wrong with the submap dataset? Or I miss something?

ahandsomeperson commented 5 years ago

oh, I just solve this problem

KangchengLiu commented 3 years ago

How is it solved?

chienerh commented 3 years ago

I also encountered the issue that the values are abnormally large. I checked the generate_submaps.m code and found out the author is storing the bin files using double. Previously, I was reading the bin file using np.float32. After changing the reading format to np.double or np.float64, I can read the file properly.