Apppublic

ShilongLiu/Grounding_DINO_demo

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

95likes

App README

Grounding DINO

📃Paper | 📽️Video | 🗯️ Github | 📯Demo on Colab | [🤗Demo on HF (Coming soon)]()

![Open In Colab](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/zero-shot-object-detection-with-grounding-dino.ipynb) \ ![PWC](https://paperswithcode.com/sota/zero-shot-object-detection-on-mscoco?p=grounding-dino-marrying-dino-with-grounded) \ ![PWC](https://paperswithcode.com/sota/zero-shot-object-detection-on-odinw?p=grounding-dino-marrying-dino-with-grounded) \ ![PWC](https://paperswithcode.com/sota/object-detection-on-coco-minival?p=grounding-dino-marrying-dino-with-grounded) \ ![PWC](https://paperswithcode.com/sota/object-detection-on-coco?p=grounding-dino-marrying-dino-with-grounded)

Official pytorch implementation of Grounding DINO, a stronger open-set object detector. Code is available now!

Highlight

—Open-Set Detection. Detect everything with language!
—High Performancce. COCO zero-shot 52.5 AP (training without COCO data!). COCO fine-tune 63.0 AP.
—Flexible. Collaboration with Stable Diffusion for Image Editting.

News

[2023/03/27] Support CPU-only mode. Now the model can run on machines without GPUs.\ [2023/03/25] A demo for Grounding DINO is available at Colab. Thanks to @Piotr! \ [2023/03/22] Code is available Now!

TODO

—[x] Release inference code and demo.
—[x] Release checkpoints.
—[ ] Grounding DINO with Stable Diffusion and GLIGEN demos.
—[ ] Release training codes.

Install

If you have a CUDA environment, please make sure the environment variable CUDA_HOME is set. It will be compiled under CPU-only mode if no CUDA available.

bash

pip install -e .

Demo

bash

CUDA_VISIBLE_DEVICES=6 python demo/inference_on_a_image.py \
  -c /path/to/config \
  -p /path/to/checkpoint \
  -i .asset/cats.png \
  -o "outputs/0" \
  -t "cat ear." \
  [--cpu-only] # open it for cpu mode

See the demo/inference_on_a_image.py for more details.

Checkpoints

<table> <thead> <tr style="text-align: right;"> <th></th> <th>name</th> <th>backbone</th> <th>Data</th> <th>box AP on COCO</th> <th>Checkpoint</th> <th>Config</th> </tr> </thead> <tbody> <tr> <th>1</th> <td>GroundingDINO-T</td> <td>Swin-T</td> <td>O365,GoldG,Cap4M</td> <td>48.4 (zero-shot) / 57.2 (fine-tune)</td> <td><a href="https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha/groundingdinoswintogc.pth">link</a></td> <td><a href="https://github.com/IDEA-Research/GroundingDINO/blob/main/groundingdino/config/GroundingDINOSwinTOGC.py">link</a></td> </tr> </tbody> </table>

Acknowledgement

Our model is related to DINO and GLIP. Thanks for their great work!

We also thank great previous work including DETR, Deformable DETR, SMCA, Conditional DETR, Anchor DETR, Dynamic DETR, DAB-DETR, DN-DETR, etc. More related work are available at Awesome Detection Transformer. A new toolbox detrex is available as well.

Thanks Stable Diffusion and GLIGEN for their awesome models.

Citation

If you find our work helpful for your research, please consider citing the following BibTeX entry.

bibtex

@inproceedings{ShilongLiu2023GroundingDM,
  title={Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection},
  author={Shilong Liu and Zhaoyang Zeng and Tianhe Ren and Feng Li and Hao Zhang and Jie Yang and Chunyuan Li and Jianwei Yang and Hang Su and Jun Zhu and Lei Zhang},
  year={2023}
}