open-mmlab/mmdetection3d
OpenMMLab's next-generation platform for general 3D object detection.
PythonApache-2.0
Pinned issues
Issues
- 2
[New Models] In BEVFusion, training unable to Achieve Official Reported Performance: NDS 71.13, mAP 68.36
#2967 opened by JiankunShi - 0
could mmdetection3d have Kitti dataset fusion Lidar and Camera ?[Feature]
#2989 opened by Chanpisey-github - 5
- 3
smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d config does not exists
#2939 opened by damavand1 - 1
- 0
[Feature] Make Lyft Dataset Optional
#2983 opened by TairuiWang - 0
[Bug] After some epochs of training pointpillars, loss and grad_norm = nan; map = 0
#2982 opened by saber-pro - 3
[Feature] You should set `PYTHONPATH` to make `sys.path` include the directory which contains your custom module
#2930 opened by guanyu1998 - 0
[Bug] img_path = data_info['images'][cam_type]['img_path'] KeyError: 'CAM2'
#2981 opened by weinixiong8964 - 2
- 1
[Bug] bevfusion image feature not working
#2951 opened by hipforth - 5
- 0
[New Models] mmdet3d是停止维护了吗
#2976 opened by GauthierLi - 0
[Bug] pip install -v -e . error
#2978 opened by yux-lab - 0
- 0
[Docs] python 文件: data_augment_utils.py 函数: box_collision_test 不能充分的判断盒子是否重叠
#2974 opened by ALLLLLecy - 0
Support for visualizing and saving image results on remote servers like colab
#2972 opened by sparshgarg23 - 2
[Bug] create_data.py with nuscenes not working
#2945 opened by Viktor1203 - 0
[Bug] Installing mmdet3d v0.17.1 meets some errors.
#2971 opened by hanzifan - 0
[Bug] Docker image build error
#2969 opened by syoungbaak - 5
- 0
[Bug] Saving results using a pretrained PETR model
#2968 opened by Ortega00 - 1
[Docs] Problems on Waymo 3d Box
#2965 opened by Wang0203 - 2
- 0
[Bug] Possibilities of accuracy improvement
#2964 opened by VeeranjaneyuluToka - 0
- 2
- 0
[Docs] No preview images for Det3DLocalVisualizer
#2960 opened by toshi-k - 0
[Bug] S3DIS数据集-DGCNN点云分割权重无法下载
#2958 opened by haoshengjia - 0
MVXNET: When I used mmdet to reproduce mvxnet, the result was nearly 10 points lower than the original?
#2950 opened by Random-junhao - 0
[Docs] cam2img for KITTI and NuScenes Dataset
#2935 opened by turtlemicro - 0
[Feature] 希望增加参数量计算量统计的支持
#2955 opened by AndrewJSong - 0
[Bug] gpu memory normal but one of gpus GPU-Util is 0 and model cant train
#2954 opened by xiongda777 - 0
- 0
In training, the actual GPU memory usage is significantly higher than the model's memory footprint
#2949 opened by nuonepeaceyy - 0
Change configuration of imvoxel net so that it can be trained to make prediction on all classes rather than just one
#2948 opened by sparshgarg23 - 2
[Bug] RuntimeError: hard_voxelize_forward_impl: implementation for device cuda:0 not found.
#2932 opened by tangX10086 - 0
[Feature] error: Could not find suitable distribution for Requirement.parse('nuscenes-devkit');when bash:python setup.py install
#2941 opened by MrGoldminer - 4
[nuScnenes] nuScenes generation extremely slow
#2936 opened by BiboyQG - 0
[Bug] TypeError: __init__() got an unexpected keyword argument 'img_backbone'
#2937 opened by Random-junhao - 0
[Bug] VOD (View-of-Delft) under 3class, when using (3+1) D data (4D radar), the effect is extremely poor or even 0.
#2934 opened by Random-junhao - 2
- 0
- 0
[Docs] Details of CBGSDataset
#2927 opened by buncybunny - 2
TRacking on 3D detection [Feature]
#2926 opened by samueleruffino99 - 1
Loss is decreasing and then increasing
#2925 opened by VeeranjaneyuluToka - 0
- 3
Misplaced 2D and 3D bboxes in DAIR-V2X-C infrastructure-side dataset in monocular 3D detection
#2921 opened by ramajoballester - 0
[Bug] failed to solve: process "/bin/sh -c pip install -r requirements/build.txt" did not complete successfully: exit code: 1
#2920 opened by eyabesbes - 0