Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (2.8%) to scientific vocabulary
Repository
ovuni_dn
Basic Info
- Host: GitHub
- Owner: rasd3
- License: apache-2.0
- Language: Python
- Default Branch: main
- Size: 10.8 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
README.md
Data Preparation
SUN-RGBD
OV-Uni3DETR에서 제공하는 train/valid pkl사용(ovuni3detrsunrgbdannos/sunrgbdinfostrainplsens10c36c.pkl, sunrgbdinfosvalwithimg.pkl). SUN-RGBD의 label은 v1과 v2가 있으며 OV-Uni3DETR에서 제공하는 pkl은 v2 기반. tools/labelv2to_v1.py 으로 v2기반 pkl을 v1으로 만들 수 있음(코드 내 디렉토리 변경필요).
ScanNet
TBD
Clip Embed
config에 ptsbboxhead/zeroshotpath='sunrgbdclipa+cnamern50manyprompt46c_coda.npy' 은 CLIP기반으로 class에 대한 text feature을 추출한것. CoDA에서 제공하는 링크를 통해 원하는 클래스를 넣어서 제작 가능
Training
| | (v2)APn | APb | APall | (v1)APn | APb | APall | | --- | --- | --- | --- | --- | --- | --- | | Baseline | 9.11 | 48.4 | 18.25 | 8.7 | 47.47 | 17.12 | | Ours | 11.22 | 50.4 | 20.34 | 10.18 | 49.33 | 18.69 |
```bash
Single GPU
python ./extratools/train.py ./projects/configs/ourssunrgbd/ourssunrgbdpc.py --work-dir ./work_dirs/ours
Multi GPU
bash ./extratools/disttrain.sh ./projects/configs/ourssunrgbd/ourssunrgbdpc.py 8 --work-dir ./workdirs/ours ```
Owner
- Name: YecheolKim
- Login: rasd3
- Kind: user
- Repositories: 2
- Profile: https://github.com/rasd3
CV
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - name: "MMDetection3D Contributors" title: "OpenMMLab's Next-generation Platform for General 3D Object Detection" date-released: 2020-07-23 url: "https://github.com/open-mmlab/mmdetection3d" license: Apache-2.0
GitHub Events
Total
- Push event: 10
- Public event: 1
Last Year
- Push event: 10
- Public event: 1
Dependencies
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- asynctest *
- codecov *
- flake8 *
- interrogate *
- isort *
- kwarray *
- lyft_dataset_sdk *
- mmcv-full <=1.6.0,>=1.4.8
- mmdet ==2.24.0
- mmsegmentation ==0.30.0
- networkx <2.3,>=2.2
- numba ==0.53.0
- numpy *
- nuscenes-devkit *
- open3d *
- plyfile *
- pytest *
- pytest-cov *
- pytest-runner *
- scikit-image *
- spconv *
- tensorboard *
- trimesh <2.35.40,>=2.35.39
- ubelt *
- waymo-open-dataset-tf-2-1-0 ==1.2.0
- xdoctest >=0.10.0
- yapf *
- docutils ==0.16.0
- m2r *
- mistune ==0.8.4
- myst-parser *
- sphinx ==4.0.2
- sphinx-copybutton *
- sphinx_markdown_tables *
- mmcv-full >=1.4.8,<=1.6.0
- mmdet ==2.24.0
- mmsegmentation ==0.30.0
- open3d *
- spconv *
- waymo-open-dataset-tf-2-1-0 ==1.2.0
- mmcv >=1.4.8
- mmdet >=2.24.0
- mmsegmentation >=0.20.1
- torch *
- torchvision *
- lyft_dataset_sdk *
- networkx >=2.2,<2.3
- numba ==0.53.0
- numpy *
- nuscenes-devkit *
- plyfile *
- scikit-image *
- tensorboard *
- trimesh >=2.35.39,<2.35.40
- asynctest * test
- codecov * test
- flake8 * test
- interrogate * test
- isort * test
- kwarray * test
- pytest * test
- pytest-cov * test
- pytest-runner * test
- ubelt * test
- xdoctest >=0.10.0 test
- yapf * test