Zixiang Zhou

This error message shows there is an issue in one subprocess. I have no idea what's wrong with it. Can you provide the environment you are running on and other...

We use only 1 task head on Waymo Open Dataset. https://github.com/TuSimple/centerformer/blob/0408b29fa728950baead73354e21240174ce5b6b/configs/waymo/voxelnet/waymo_centerformer.py#L6-L8

Hi there! To use the code on your custom dataset, you'll need to write a new dataset class and converter. You can refer to either of these two examples: [waymo](https://github.com/TuSimple/centerformer/tree/master/det3d/datasets/waymo)...

I used ``prenorm`` inside each layer. https://github.com/TuSimple/centerformer/blob/96aa37503dc900d1aebeb7c1086c33bbd0c01d26/det3d/models/utils/transformer.py#L218-L238

Sorry, I haven't tried Add&Norm after each layer. Do you have experience with this before and would the results be better if you used this implementation?

1. In the newer version of Centerpoint, the global translation augmentation is also used: https://github.com/tianweiy/CenterPoint/blob/c4b4e0fc97ec6d42d6a31f559816d3305abdf750/configs/waymo/voxelnet/waymo_centerpoint_voxelnet_three_sweeps_20e_iou_pred.py#L116 2. I used ``np.random.uniform`` based on other published papers and haven't tried ``np.random.normal``. I don't...

> some sonfused... Do these data augmenting strategies ensure consistency between sequential frames? How exactly is the copy-paste strategy designed between sequential frames? The pasted object will be added to...

> Thanks for releasing the nuscenes dataset code support. I have some questions about the implement of the multi-tasks. I see in the code that you define obj_num=500 for each...

Hello, thanks for your interest in our work. Sorry, I currently do not have access to my previous pretrained weight. If you need to lower the memory cost, you can...

> Hello, in order to reproduce the waymo results by my own, I trained CenterFormer on waymo and tried to get the performance evaluation like that shown in the README:...