| Collections: | |
| - Name: MVX-Net | |
| Metadata: | |
| Training Data: KITTI | |
| Training Techniques: | |
| - AdamW | |
| Training Resources: 8x V100 GPUs | |
| Architecture: | |
| - Feature Pyramid Network | |
| - Dynamic Voxelization | |
| Paper: | |
| URL: https://arxiv.org/abs/1904.01649 | |
| Title: 'MVX-Net: Multimodal VoxelNet for 3D Object Detection' | |
| README: configs/mvxnet/README.md | |
| Code: | |
| URL: https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/models/detectors/mvx_two_stage.py#L20 | |
| Version: v0.5.0 | |
| Models: | |
| - Name: dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class | |
| Alias: mvxnet_kitti-3class | |
| In Collection: MVX-Net | |
| Config: configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py | |
| Metadata: | |
| Training Memory (GB): 6.7 | |
| Results: | |
| - Task: 3D Object Detection | |
| Dataset: KITTI | |
| Metrics: | |
| mAP: 63.5 | |
| Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class-8963258a.pth | |