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 generating the dataset #5

Closed JuanDuGit closed 5 years ago

JuanDuGit commented 5 years ago

Hi, thanks for your code. I have a question regarding the datasets you are using to generate the training tuples. In the file generate_training_tuples_baseline.py, line 21, index_list=range(len(all_folders)-1) , it seems that you are using all runs except for the last sequence. Any reason for this? Or did I miss something? Thanks for your help in advance!

mikacuy commented 5 years ago

Hi,

I apologize for the delayed response. The experiments were ran for all sequences. That code can be modified to fit your file arrangements. Thanks