Data

Tools

Indexes

Applications

Experiments

Open Source Science

mm-grounding-dino-fine-tune

mm-grounding-dino-for-training

https://github.com/pardistaghavi/mm-grounding-dino-fine-tune

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 (6.4%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

mm-grounding-dino-for-training

Basic Info
  • Host: GitHub
  • Owner: PardisTaghavi
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 13.4 MB
Statistics
  • Stars: 4
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

Overview

This is just a copy of original repo (https://github.com/open-mmlab/mmdetection/tree/main) for personal fine-tuning purposes. Please refer to the original library for more details.

Fine-tuning Few-shot mm-Gdino on Cityscapes Dataset

Installation

Based on https://mmdetection.readthedocs.io/en/latest/get_started.html

```bash apt-get update && apt-get install -y emacs-nox python3-pip

pip install gdown openmim pip install torch torchvision mim install mmengine mim install "mmcv>=2.0.0" mim install mmdet ```

Artifacts

Use gdown to download the artifacts.

Few-shot Labeled Data

Dataset: https://drive.google.com/file/d/143yo4N2guTVst824xehFqgdHSZAHQbr/view?usp=sharing Pretrained model: https://drive.google.com/file/d/1QDEBxPzcSqOpXvzSpIX0pv68wurrG05/view?usp=sharing

bash gdown https://drive.google.com/uc?id=143yo4N2guTVst_824xehFqgdHSZAHQbr gdown https://drive.google.com/uc?id=1Q_DEBxPzcSqOpXvzSpIX0pv68wurrG05

Few-shot Labeled Data + Unlabeled Data [self-training]

bash gdown https://drive.google.com/uc?id=1trqXGRW9aSSVeZUTFFdNP1lYj-leD9Od gdown https://drive.google.com/uc?id=1Q_DEBxPzcSqOpXvzSpIX0pv68wurrG05

Usage

In configs/mmgroundingdino/cityscapes/groundingdinoswin-lfinetunecityscapes186fewshotpretrainall.py,

1) change "dataroot" to the dataset path. 2) change "loadfrom" to the pretrained model path.

bash ./tools/dist_train.sh configs/mm_grounding_dino/cityscapes/grounding_dino_swin-l_finetune_cityscapes_186_fewshot_pretrain_all.py 2

Cityscapes Result

Few shot labeled data (10imgs/cls)

| LR/Scheduler | MultiStep(weight decay0.01) | |----------------|---------------------------------| | 5e-5 | AP{bbox} 53.1 | | 1e-5 | AP{bbox} 51.5 |

Few shot labeled data (10imgs/cls) + unlabeled data(1860 imgs) for self-training

| LR/Scheduler | MultiStep(weight decay0.01) | |----------------|---------------------------------| | 5e-5 | AP_{bbox} 54.20 |

#######################################333

ADE20k Result

Few shot labeled data (10imgs/cls)

| LR/Scheduler | MultiStep(weight decay0.01) | |----------------|---------------------------------| | 5e-5 | AP{bbox} TBA | | 1e-5 | AP{bbox} TBA |

Few shot labeled data (10imgs/cls) + unlabeled data(1860 imgs) for self-training

| LR/Scheduler | MultiStep(weight decay0.01) | |----------------|---------------------------------| | 5e-5 | AP_{bbox} TBA |

Owner

  • Name: Pardis Taghavi
  • Login: PardisTaghavi
  • Kind: user
  • Location: College Station, Texas

Graduate research assistant and PhD student working on perception of self-driving cars

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
  • Watch event: 4
  • Member event: 1
  • Push event: 15
  • Create event: 2
Last Year
  • Watch event: 4
  • Member event: 1
  • Push event: 15
  • Create event: 2

Dependencies

.circleci/docker/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
docker/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
docker/serve/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
docker/serve_cn/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
requirements/albu.txt pypi
  • albumentations >=0.3.2
requirements/build.txt pypi
  • cython *
  • numpy *
requirements/docs.txt pypi
  • 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
requirements/mminstall.txt pypi
  • mmcv >=2.0.0rc4,<2.2.0
  • mmengine >=0.7.1,<1.0.0
requirements/multimodal.txt pypi
  • fairscale *
  • jsonlines *
  • nltk *
  • pycocoevalcap *
  • transformers *
requirements/optional.txt pypi
  • cityscapesscripts *
  • emoji *
  • fairscale *
  • imagecorruptions *
  • scikit-learn *
requirements/readthedocs.txt pypi
  • mmcv >=2.0.0rc4,<2.2.0
  • mmengine >=0.7.1,<1.0.0
  • scipy *
  • torch *
  • torchvision *
  • urllib3 <2.0.0
requirements/runtime.txt pypi
  • matplotlib *
  • numpy *
  • pycocotools *
  • scipy *
  • shapely *
  • six *
  • terminaltables *
  • tqdm *
requirements/tests.txt pypi
  • 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
requirements/tracking.txt pypi
  • mmpretrain *
  • motmetrics *
  • numpy <1.24.0
  • scikit-learn *
  • seaborn *
requirements.txt pypi
setup.py pypi
Dockerfile docker
  • nvcr.io/nvidia/pytorch 24.10-py3 build