A question about KITTI raw dataset

xuanyuzhou98 / SqueezeSegV2

Implementation of SqueezeSegV2, Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud

BSD 2-Clause "Simplified" License

233 stars 69 forks source link

A question about KITTI raw dataset #4

Closed kxhit closed 5 years ago

kxhit commented 5 years ago

Thanks for sharing your work! I have a problem about your lidar_2d data, which only has 10848 .npy files. But there are 12915 files raw data with tracklets in KITTI dataset. Do you throw away some files? Could you verify this problem? Thanks! Waiting for your reply. The same issue is here: https://github.com/BichenWuUCB/SqueezeSeg/issues/35

jrbin commented 5 years ago

The interested objects are per. cyl. car. Only the 10848 images include these objects.

kxhit commented 5 years ago

I see, thank you! I think the images that do not contain these objects can be treated as negative samples. Maybe it doesn't matter, because the negative samples are far more than the positive samples.