-
I train the model on 3 RTX3090 and finish the first epoch after about 10hours ,but its stuck on the end of the first epoch before save checkpoint. I use this command to train.
torchpack dist-run -np …
-
Hi @yichen928 ,
SparseFusion is really a nice work, but I wonder how did you obtain the initial weights: sparsefusion_voxel0075_SwinT_initial and sparsefusion_voxel0075_R50_initial?
-
Thanks for providing this package. I am successfully able to use the torchpack dist-run -np ${_ngpu} command on a slurm cluster when using only 1 node.
Could you please explain how to use this with …
-
Thank you for your amazing work.
I noticed in your article that: “Following BEVFormerv2, the ViT-Large is pre-trained on Objects365 and COCO dataset. " But it seems that neither ViT-L nor Objects…
-
Hi all,
I am having two AWS machines with Ubuntu 16.04 Ubuntu. I installed OpenMPI 4.0. I run the standard Tensorflow example with MNIST dataset.
The output that I got from running the followin…
-
Hi,
thank you for your great work to organize such a challenge.
I follow the [getting_started](https://github.com/CVPR2023-3D-Occupancy-Prediction/CVPR2023-3D-Occupancy-Prediction/blob/main/docs…
-
If all nuScenes, nuScenes-lidarseg and nuImages annotations are allowed to use during training?
Thanks!
-
use docker enviroment , but meet some error, my server has 4*2080TI GPU with driver 515.65.01
```
root@730873b34ac1:/projects/perception3d/bevfusion# torchpack dist-run -np 4 python tools/train.py c…
-
I have tried traing the fusion model without pretrain weights on nuimages and got about 1.0 NDS lower. If I use the pretrain weights, i can get the reported results(about 71 NDS).
Therefore, I wonde…
-
Hello everyone
Thank you very much for your attractive project.
As you said in the instructions, I went and installed the libraries and made the folders and put the `pkl` related to the `V1.0-mini `…