Add support for VoxelNeXt #1309
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@malicd Thank you for your reminder. We will also include these documentations in pcdet. Thanks Yukang @yukang2017 . |
|
@malicd Thanks. We will merge them soon. |
|
Note that it seems that there are some bugs for training VoxelNeXt on spconv 2.2/2.3 version. We are trying to fix it. Before we finish this, please use spconv in 2.1, e.g., spconv==2.1.25 for training! |
ahmedius2
pushed a commit
to CSL-KU/Anytime-Lidar
that referenced
this pull request
Apr 19, 2023
* VoxelNeXt
|
Did this question solved? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi,
This is a pull request for VoxelNeXt. VoxelNeXt is a simple, and fully-sparse 3D object detector. The core idea is to predict objects directly upon sparse voxel features. This work has been accepted by CVPR 2023.
For this pull request, it contains
(1) backbone, head, detector in
pcdet/models.(2) argoverse2 dataset in
pcdet/datasets.(3) config files for nuScenes/Waymo/Argoverse2 datasets in
tools/cfgs.(4) updated README that includes the introduction of VoxelNeXt.
(5) some sparse loss functions in
pcdet/utils/loss_utils.py.(6) some utils in
pcdet/models/model_utils/centernet_utils.py.I have already tested both inference and training upon this code. Please feel free to contact me if there are any issues.
Regards,
Yukang Chen