search

Vegeta2020 / SE-SSD

SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud, CVPR 2021.
Apache License 2.0
811 stars 128 forks source link

About the division of KITTI training dataset #90

Closed Say2L closed 2 years ago

Say2L commented 2 years ago

Hello, I want to know how you divided the official KITTI training dataset when you get the results of KITTI test dataset?

Vegeta2020 commented 2 years ago

Hi, we trained the model on the trainval set to get the results on the test set, which means we didn't divide but use the complete training dataset.

Say2L commented 2 years ago

Thanks for your reply.

Tongjiaxun commented 1 year ago

Hi, we trained the model on the trainval set to get the results on the test set, which means we didn't divide but use the complete training dataset.

So, if no valid set, how to choose the best model?