search

mikacuy / pointnetvlad

PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition, CVPR 2018
MIT License
351 stars 72 forks source link

About training and test data split #14

Open PSYZ1234 opened 4 years ago

PSYZ1234 commented 4 years ago

Hi, thanks for your code! I have a question about training and test data split in generate_training_tuples_baseline.py. Line 30, you set p1 = [5735712.768124,620084.402381], p2 = [5735611.299219,620540.270327], p3 = [5735237.358209,620543.094379], and p4 = [5734749.303802,619932.693364]. I think they are the mean value of "northing" and "easting". I just want to know how to get the four different mean values. And why you choose four mean values not five or more. Thanks for your help in advance!

yopi1838 commented 3 years ago

Pardon for my lack of understanding but I think that's just her way of splitting the datasets. you can see in the definition of check_in_test function. If the specified northing and easting from the datasets are within the defined points (+- x_width and y_width), the point cloud is included into the testdataset, else it will be added into the traindataset. I think you can add more points if you wanted to filter more of the raw dataset into the testdataset.

yopi1838 commented 3 years ago

Pardon for my lack of understanding but I think that's just her way of splitting the datasets. you can see in the definition of check_in_test function. If the specified northing and easting from the datasets are within the defined points (+- x_width and y_width), the point cloud is included into the testdataset, else it will be added into the traindataset. I think you can add more points if you wanted to filter more of the raw dataset into the testdataset.

image This was further shown in her paper where she stated that the regions were randomly selected.