mmdetection-satellite-dinov2
mmdetection-satellite-dinov2
Science Score: 67.0%
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
Found 2 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (7.4%) to scientific vocabulary
Repository
mmdetection-satellite-dinov2
Basic Info
- Host: GitHub
- Owner: wri
- License: apache-2.0
- Language: Jupyter Notebook
- Default Branch: main
- Size: 19.3 MB
Statistics
- Stars: 21
- Watchers: 5
- Forks: 1
- Open Issues: 1
- Releases: 0
Metadata Files
README.md
mmdetection-satellite-dinov2
mmdetection-satellite-dinov2
[Paper][ArxiV [same content]] [Blog] [BibTeX]
Overview
This repository contains the (WORK IN PROGRESS) integration of the DiNOV2 SSL layer from Meta and WRI with MMDetection. MMdet 3.X has been updated to include the SSL layer as a backbone. Example configuration for training a ViTDet with a Cascade RCNN head on a COCO-style dataset can be found in the configs-dino folder.
Getting started
An example notebook can be found here to train a DINO DETR with the DINOv2 ViT backbone.
Detrex
Improvements to the DINO DETR detection model have been made in the past two years. Most notable are Rank DETR and Stable DINO. These models are implemented in Detrex, which is built on top of Detectron2.
Configuration files to train Rank DETR with the DINOv2 Vit-L backbone can be found here
Configuration files to train Stable DINO with the DINOv2 Vit-L backbone can be found here
Owner
- Name: World Resources Institute
- Login: wri
- Kind: organization
- Email: datalab@wri.org
- Location: Washington, DC
- Website: https://wri.org
- Repositories: 207
- Profile: https://github.com/wri
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - name: "MMDetection Contributors" title: "OpenMMLab Detection Toolbox and Benchmark" date-released: 2018-08-22 url: "https://github.com/open-mmlab/mmdetection" license: Apache-2.0
GitHub Events
Total
- Issues event: 1
- Watch event: 12
- Push event: 5
- Fork event: 1
Last Year
- Issues event: 1
- Watch event: 12
- Push event: 5
- Fork event: 1
Dependencies
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- asynctest *
- cityscapesscripts *
- codecov *
- cython *
- emoji *
- fairscale *
- flake8 *
- imagecorruptions *
- instaboostfast *
- interrogate *
- isort ==4.3.21
- jsonlines *
- kwarray *
- matplotlib *
- memory_profiler *
- mmcv <2.2.0,>=2.0.0rc4
- mmengine <1.0.0,>=0.7.1
- mmpretrain *
- mmtrack *
- motmetrics *
- nltk *
- numpy <1.24.0
- numpy *
- onnx ==1.7.0
- onnxruntime >=1.8.0
- parameterized *
- prettytable *
- protobuf <=3.20.1
- psutil *
- pycocoevalcap *
- pycocotools *
- pytest *
- scikit-learn *
- scipy *
- seaborn *
- shapely *
- six *
- terminaltables *
- tqdm *
- transformers *
- ubelt *
- xdoctest >=0.10.0
- yapf *
- albumentations >=0.3.2
- cython *
- numpy *
- docutils ==0.16.0
- myst-parser *
- sphinx ==4.0.2
- sphinx-copybutton *
- sphinx_markdown_tables *
- sphinx_rtd_theme ==0.5.2
- urllib3 <2.0.0
- mmcv >=2.0.0rc4,<2.2.0
- mmengine >=0.7.1,<1.0.0
- fairscale *
- jsonlines *
- nltk *
- pycocoevalcap *
- transformers *
- cityscapesscripts *
- emoji *
- fairscale *
- imagecorruptions *
- scikit-learn *
- mmcv >=2.0.0rc4,<2.2.0
- mmengine >=0.7.1,<1.0.0
- scipy *
- torch *
- torchvision *
- urllib3 <2.0.0
- matplotlib *
- numpy *
- pycocotools *
- scipy *
- shapely *
- six *
- terminaltables *
- tqdm *
- asynctest * test
- cityscapesscripts * test
- codecov * test
- flake8 * test
- imagecorruptions * test
- instaboostfast * test
- interrogate * test
- isort ==4.3.21 test
- kwarray * test
- memory_profiler * test
- nltk * test
- onnx ==1.7.0 test
- onnxruntime >=1.8.0 test
- parameterized * test
- prettytable * test
- protobuf <=3.20.1 test
- psutil * test
- pytest * test
- transformers * test
- ubelt * test
- xdoctest >=0.10.0 test
- yapf * test
- mmpretrain *
- motmetrics *
- numpy <1.24.0
- scikit-learn *
- seaborn *