-
When I run command to create data, the error happened
```
(pt110) hitbuyi@hitbuyi-Dell-G15-5511:~/PycharmProjects/pytorch_project/BEVFormer$ python tools/create_data.py nuscenes --root-path ./dat…
-
Hello, Senior Li.I'm reproducing your BEVFormer work recently. The GPU server I'm using is Tesla p100 16g*8, that I want use it to run BEVFormer_small. When I set "with_cp=False",it reports that CUDA …
-
@Lizhuoling Hi, thanks for your great work. Regarding Table 4, I wonder why VoxelFormer looks more lightweight than BEVFormer. I think if all the architectural specifications are aligned between them,…
-
I have only one GPU, when train tiny bevformer model, the programe indicates CUDA out of memory, where to reduce the batch size?
-
Very great work.
https://github.com/fundamentalvision/BEVFormer#catalog
```
BEVFormerV2 HyperQuery
BEVFormerV2 Optimization, including memory, speed, inference.
BEV Segmentation checkpoints…
-
I got 2 gpus on my server,I run the train as ./tools/dist_train.sh ./projects/configs/bevformer/bevformer_base.py 2.
It says that CUDA out of memory. Tried to allocate 252.00 MiB (GPU 0; 23.69 GiB to…
-
I use "python ./tools/test.py ./projects/configs/bevformer/bevformer_base.py ./ckpts/r101_dcn_fcos3d_pretrain.pth --out ./results/result.pkl --show True --show_dir ./results/" to generate test results…
-
-
嗨，您好！
我打算在orin上部署bevformer，请问可以直接迁移部署吗？
期待您的回复！
-
Version：
Pytorch：1.10.1
Cuda：11.1
chamferdist：1.0.0
Traceback (most recent call last):
2024-05-15T10:49:54.908855819Z File "./tools/test.py", line 266, in
2024-05-15T10:49:54.908901447Z …