lidar-bonnetal
lidar-bonnetal copied to clipboard
PRBonn
Semantic and Instance Segmentation of LiDAR point clouds for autonomous driving
Hi, I found you mentioned the speed of rangenet++ is 5fps(64x2048) on Jetson agx, but I wonder how's the speed after tensorrt on Jetson agx? @jbehley
Thank you for sharing your codes. I found that all backbones call `detach()` in skip-connections. For example: https://github.com/PRBonn/lidar-bonnetal/blob/5a5f4b180117b08879ec97a3a05a3838bce6bb0f/train/backbones/squeezesegV2.py#L156 Could you tell me where this idea is from? I cannot find...
Hi, thanks for your excellent works! But when I try to train by run "./train.py -d /path/to/dataset -ac /config/arch/squeezesegV2.yaml -l /path/to/log", an IndexError was caught, see:  I have check...
Many thanks to your team for the open source code,I want to use my own dataset to train in lidar-bonnetal, and i add some tags in the dataset that are...
Hi, currently installing depends on Ubuntu 22.04.3. Looks like [tensorflow](https://www.tensorflow.org/install/source#install_gpu_support_optional_linux_only)=1.13.1 runs on CPU: tensorflow-1.13.1 python 3.7 GCC 4.8 GPU: tensorflow_gpu-1.13.1 python 3.7 GCC 4.8 CuDNN 7.4 Cuda 10.0 I'll be...
- I cloned the repository, downloaded the Semantic KITTI dataset, downloaded the pretrained models. - The dataset structure is as follows:  - I installed the mentioned packages, and libraries...
Hello. Thank you for your work and support by making this project an open source. Recently, I am trying to work with lidar-bonnetal to get predictions from pretrained model. I...
Dear authors, I'm new in the field, and my question might be fundamental. I'm trying to figure out a way to index the unused points when I project it to...
Can you please tell where are the pretrained models
