search

xtreme1-io / xtreme1

Xtreme1 is an all-in-one data labeling and annotation platform for multimodal data training and supports 3D LiDAR point cloud, image, and LLM.
https://www.basic.ai
Apache License 2.0
895 stars 143 forks source link

Seeking Detailed Information on the Model Architecture and Weight File Used in Basic AI for LiDAR-Camera Fusion Annotation #230

Closed jotamotk closed 1 week ago

jotamotk commented 7 months ago

Hello, Basic AI Team

I started annotating on the datasets of LiDAR Fusion Trial. I used Basic LiDAR Object Detection model. The results are so good. I'm wondering that how worked it. So I red your documents and I understood that Lidar-camera Fusion (Frame series) Annotation uses OpenPCDet. That annotates 3D point Cloud. However, I couldn't know which model (architecture) and weight file are used on Basic AI. Could I know the information.

Regards, Silva

ShirleySprite commented 7 months ago

Hello! The detailed configuration of the model can be found in this file: https://github.com/xtreme1-io/point-cloud-object-detection/blob/main/pcdet_open/cfgs/nuscenes_models/cbgs_voxel0075_res3d_centerpoint.yaml

silva21d commented 6 months ago

Hello! The detailed configuration of the model can be found in this file: https://github.com/xtreme1-io/point-cloud-object-detection/blob/main/pcdet_open/cfgs/nuscenes_models/cbgs_voxel0075_res3d_centerpoint.yaml

@ShirleySprite Thank you for your answer I confirmed the source code and understand the algorithm.