Hi,
i am new to TAO ToolKit.
I am following the TAO Toolkit Quick Start Guide and got stuck with this error.
I am getting the launcher CLI running.
Can login into the NGC Docker registry.
Create a conda env.
Install the TAO Launcher.
Download the pretrained model.
Start the notebook.
and on that command:
!tao pointpillars run python $SPECS_DIR/gen_lidar_points.py -p $DATA_DOWNLOAD_DIR/training/velodyne
-c $DATA_DOWNLOAD_DIR/training/calib
-i $DATA_DOWNLOAD_DIR/training/image_2
-o $DATA_DOWNLOAD_DIR/train/lidar
I am getting this error:
2023-12-05 10:32:36,088 [INFO] root: Registry: [‘nvcr.io’]
2023-12-05 10:32:36,151 [INFO] tlt.components.instance_handler.local_instance: Running command in container: nvcr.io/nvidia/tao/tao-toolkit:4.0.0-pyt
2023-12-05 10:32:36,475 [WARNING] tlt.components.docker_handler.docker_handler:
Docker will run the commands as root. If you would like to retain your
local host permissions, please add the “user”:“UID:GID” in the
DockerOptions portion of the “/home/helge/.tao_mounts.json” file. You can obtain your
users UID and GID by using the “id -u” and “id -g” commands on the
terminal.
Traceback (most recent call last):
File “/cv_samples_v1.4.1/pointpillars/specs/gen_lidar_points.py”, line 9, in
from pointcloud.pointpillars.pcdet.utils.calibration_kitti import (
ModuleNotFoundError: No module named ‘pointcloud’
2023-12-05 10:32:37,539 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.
I could not find a topic about it, maybe someone knows the solution.