-
Hello, in the forward function of NuScenesImVoxelNeck you swap x and y dimension as [https://github.com/saic-vul/imvoxelnet/blob/master/mmdet3d/models/necks/imvoxelnet.py#L151](url).
What's the insig…
-
In the README, you tell us to set dataset argument to nuscenes_monocular when creating nuscenes multiview dataset. I follow your instruction but just change the version from 'v1.0-trainval' to 'v1.0-m…
-
Hello, I try to understand the transformation you do on 'tmp_box' in the following code:
[https://github.com/saic-vul/imvoxelnet/blob/master/tools/data_converter/nuscenes_monocular_converter.py#L108-…
-
Can not visualize the output results based on SUN RGB-D!
python tools/test.py configs/imvoxelnet/imvoxelnet_sunrgbd.py work_dirs/epoch_12.pth --show --show-dir work_dirs/imvoxelnet_sunrgbd/results
…
-
Hi, @Tai-Wang and mmdetection3d team,
This issue continues the discussion in https://github.com/saic-vul/imvoxelnet/issues/7. If you are sure, it would be great to have ImVoxelNet in this codebase,…
-
Hi. As far as I understand from this line: https://github.com/open-mmlab/mmdetection3d/blob/7fec1d533bacf5b5c89d456f65c775c3cc458c72/mmdet3d/models/detectors/imvoxelnet.py#L47
ImVoxelNet only uses on…
-
The error is below.
`Use load_from_local loader
[ ] 0/6019, elapsed: 0s, ETA:Traceback (most recent call last):
File "tools/test.py", line 214, in…
-
-
Hi, thanks for sharing your great work!
I want to enlarge voxel size for less memory usage. I notice that there are two factors affect 3d voxel shape: VOXEL_SIZE and POINT_CLOUD_RANGE. In `POINT_CLOU…
-
Hi, author,
i want to realize one demo, its input is two or three images taken by camera from different views of one object and the output is 3D bounding boxes of the object.
can imvoxelnet realiz…