Running the Demo throws RuntimeError

[JensStaub]

When trying to run the demo.py using the command

~/Development/OpenPCDet/tools$ python3 demo.py --cfg_file cfgs/kitti_models/pointpillar.yaml --ckpt /home/data/Development/models/pointpillar_7728.pth --data_path /home/data/Development/datasets/kitti/velodyne_points/001005.bin

I get the following Error:

`
Traceback (most recent call last):
File "/home/user/Development/OpenPCDet/tools/demo.py", line 18, in
from pcdet.datasets import DatasetTemplate
File "/home/user/Development/OpenPCDet/pcdet/datasets/init.py", line 15, in
from .argo2.argo2_dataset import Argo2Dataset
File "/home/user/Development/OpenPCDet/pcdet/datasets/argo2/argo2_dataset.py", line 15, in
from .argo2_utils.so3 import yaw_to_quat, quat_to_yaw
File "/home/user/Development/OpenPCDet/pcdet/datasets/argo2/argo2_utils/so3.py", line 10, in
def quat_to_mat(quat_wxyz: Tensor) -> Tensor:
File "/usr/local/lib/python3.10/dist-packages/torch/jit/_script.py", line 1395, in script
fn = torch._C._jit_script_compile(
File "/usr/local/lib/python3.10/dist-packages/torch/jit/_recursive.py", line 1003, in try_compile_fn
return torch.jit.script(fn, _rcb=rcb)
File "/usr/local/lib/python3.10/dist-packages/torch/jit/_script.py", line 1395, in script
fn = torch._C._jit_script_compile(
RuntimeError:
cannot statically infer the expected size of a list in this context:
File "/usr/local/lib/python3.10/dist-packages/kornia/geometry/conversions.py", line 553

# this slightly awkward construction of the output shape is to satisfy torchscript
output_shape = [*list(quaternion.shape[:-1]), 3, 3]
                ~~~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
matrix = matrix_flat.reshape(output_shape)

'quaternion_to_rotation_matrix' is being compiled since it was called from 'quat_to_mat'
File "/home/user/Development/OpenPCDet/pcdet/datasets/argo2/argo2_utils/so3.py", line 19
(...,3,3) 3D rotation matrices.
"""
return C.quaternion_to_rotation_matrix(
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
quat_wxyz, order=C.QuaternionCoeffOrder.WXYZ
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
)
`

I am testing on the following system:

• Ubuntu 22.04
• python3.10
• CUDA 12.3
• torch 2.2.1
• kornia 0.7.1

I downloaded the KITTI dataset and the checkpoints from the website linked in the README.

Additionally I have also tried it with the Docker image built from the cu116_Dockerfile, but with the same error.

Does anybody know why this error is popping up?

[Jacobi93]

i got the same error

[JensStaub]

As mentioned here:
#1522
I downgraded "kornia" to version 0.5.8 and it is working now.