fish

I use multi-GPU trainning,but errors occurs: ``` Traceback (most recent call last): File "./train.py", line 131, in main() File "./train.py", line 82, in main model = MMDistributedDataParallel(model.cuda(),find_unused_parameters=True) File "/home/ubuntu-502/xu/CIA-SSD/envs/CIA-SSD/lib/python3.6/site-packages/torch/nn/parallel/distributed.py", line...

Thank you for your wonderful work. The paper you published is trained with batch_size16. But when I train on a single 2080Ti with batch_size =2, the performance is better than...

Hi， can you release YAML to test on 3 classes? Thank you!

effect on other models

1

Thanks for your excellent work and open source for everyone to learn. But if migrate this method to another model, for example, voxel rcnn. I just use YAML file of...

val result 3D AP always 0.00000

5

Hi,thank you for your excellent work. But some error occurs,I hope you can give me some suggestions. When I train the model.the 3D result is always ``` Car [email protected], 0.70,...

hi，I have made all conf、package,but I do not how to run the sim and EKF pacage. * it only need I run ./ExtendedKF,then sim can run * ./ExtendedKF and sim...

``` |_dataloaders |_datasets |_city.py ``` `from mypath import Path` Can't find the mypath package or dir,how can I solve it?thank you.

Hi,Did you evaluate it for any performance improvements?

weights and training preparation

1

Can you plan to release pre-trained weights and add installation readme and dataset preparation readme?