Chaoda Zheng

It could be related to the dataset. Seems that your data is damaged and thus the number of points within object bb is always zeros. Please make sure your dataset...

Could you show more details of the error message? Have you visualized your data to make sure that they are not corrupted?

The config file for training KITTI Pedestrian is just the same as that we used for Car. However, since the Pedestrian has much less training data than Car in KITTI,...

As I said, the config is the same except for the batch size. Could you please provide more details about your platform (e.g. Cuda version, PyTorch version, GPU specs)? Can...

Hi there, I've tested the code twice with the same config file on a similar platform as yours (a single v100 with pytorch 1.8.0 and CUDA 11.1). In my experiments,...

Yes, I passed it in the command line. Actually the batch size in the config file is useless and confusing. I will remove it soon.

> Thanks a lot for the reply. Did your pass command line parameters like `--batch size 64` in your training, because it seems that the batch size in your config...

> Below is the result of my bs64 epoch180 Pedestrian experiment > > Seems that there are better checkpoints in this training and they are close to our reported result....

We do this dynamic visualization using the **open3d** library.

Yes, we would like to do so. But Waymo dataset is too large and currently we cannot find a suitable cloud drive or open web server to store those files.