Closed Say2L closed 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.
Thanks for your reply.
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?
Hello, I want to know how you divided the official KITTI training dataset when you get the results of KITTI test dataset?