search

TuSimple / centerformer

Implementation for CenterFormer: Center-based Transformer for 3D Object Detection (ECCV 2022)
MIT License
293 stars 28 forks source link

Well trained weights on nuscenes #19

Open hehualin-tut opened 1 year ago

hehualin-tut commented 1 year ago

Hello, first of all, thank you for your excellent work. I would like to ask whether there is a trained weight on nuscenes, because my computer can not run training, so I would like to use the trained model to evaluate and see the effect.

By the way, how can I change the batchsize or some other operation to make the GPU demand smaller

edwardzhou130 commented 1 year ago

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 try changing the following parameters:

  1. batch size -> 1 or 2 https://github.com/TuSimple/centerformer/blob/5a949b88ed7bb15aafb39bf78c95f1452063ebea/configs/nusc/nuscenes_centerformer_separate_detection_head.py#L188
  2. channel size https://github.com/TuSimple/centerformer/blob/5a949b88ed7bb15aafb39bf78c95f1452063ebea/configs/nusc/nuscenes_centerformer_separate_detection_head.py#L34-L69
  3. voxel size -> [0.1, 0.1, 0.2] https://github.com/TuSimple/centerformer/blob/5a949b88ed7bb15aafb39bf78c95f1452063ebea/configs/nusc/nuscenes_centerformer_separate_detection_head.py#L32