Grounded-Segment-Anything

We plan to create a very interesting demo by combining Grounding DINO and Segment Anything! Right now, this is just a simple small project. We will continue to improve it and create more interesting demos. And thanks for the community users provide the colab demo for us.

We are very willing to help everyone share and promote new projects based on Segment-Anything, we highlight some excellent projects here: Highlight Extension Projects. You can submit a new issue (with project tag) or a new pull request to add new projects' links.

Why this project?

The core idea behind this project is to combine the strengths of different models in order to build a very powerful pipeline for solving complex problems. And it's worth mentioning that this is a workflow for combining strong expert models, where all parts can be used separately or in combination, and can be replaced with any similar but different models (like replacing Grounding DINO with GLIP or other detectors / replacing Stable-Diffusion with ControlNet or GLIGEN/ Combining with ChatGPT).

Segment Anything is a strong segmentation model. But it needs prompts (like boxes/points) to generate masks.
Grounding DINO is a strong zero-shot detector which is capable of to generate high quality boxes and labels with free-form text.
The combination of Grounding DINO + SAM enable to detect and segment everything at any levels with text inputs!
The combination of BLIP + Grounding DINO + SAM for automatic labeling system!
The combination of Grounding DINO + SAM + Stable-diffusion for data-factory, generating new data!

Grounded-SAM

Grounded-SAM + Stable-Diffusion Inpainting: Data-Factory, Generating New Data!

BLIP + Grounded-SAM: Automatic Label System!

Using BLIP to generate caption, extract tags and using Grounded-SAM for box and mask generating. Here's the demo output:

Imagine Space

Some possible avenues for future work ...

Automatic image generation to construct new datasets.
Stronger foundation models with segmentation pre-training.
Collaboration with (Chat-)GPT.
A whole pipeline to automatically label image (with box and mask) and generate new image.

More Examples

Tips

If you want to detect multiple objects in one sentence with Grounding DINO, we suggest seperating each name with . . An example: cat . dog . chair .

🔥 What's New

🆕 Release the interactive fashion-edit playground in here. Run in the notebook, just click for annotating points for further segmentation. Enjoy it!
🆕 Checkout our related human-face-edit branch here. We'll keep updating this branch with more interesting features. Here are some examples:

💡 Highlight Extension Projects

Zero-Shot Anomaly Detection by Yunkang Cao
EditAnything: ControlNet + StableDiffusion based on the SAM segmentation mask by Shanghua Gao and Pan Zhou
IEA: Image Editing Anything by Zhengcong Fei
SAM-MMRorate: Combining Rotated Object Detector and SAM by Qingyun Li and Xue Yang
Awesome-Anything by Gongfan Fang
Prompt-Segment-Anything by Rockey
WebUi for Segment-Anything! Grounding-SAM is on the way! by Chengsong Zhang
Inpainting Anything: Inpaint Anything with SAM + Inpainting models by Tao Yu
Segment Anything and Name It: combining Segment-Anything with GLIP & Visual ChatGPT & VLPart by Shoufa Chen and Peize Sun
Narapi-SAM: Integration of Segment Anything into Narapi (A nice viewer for SAM) by MIC-DKFZ
Grounded Segment Anything Colab by camenduru

📑 Catelog

Grounding DINO Demo
Grounding DINO + Segment Anything Demo
Grounding DINO + Segment Anything + Stable-Diffusion Demo
BLIP + Grounding DINO + Segment Anything + Stable-Diffusion Demo
Hugging Face Demo
Colab demo

📖 Notebook Demo

See our notebook file as an example.

🛠️ Installation

The code requires python>=3.8, as well as pytorch>=1.7 and torchvision>=0.8. Please follow the instructions here to install both PyTorch and TorchVision dependencies. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.

Install Segment Anything:

python -m pip install -e segment_anything

Install Grounding DINO:

python -m pip install -e GroundingDINO

Install diffusers:

pip install --upgrade diffusers[torch]

The following optional dependencies are necessary for mask post-processing, saving masks in COCO format, the example notebooks, and exporting the model in ONNX format. jupyter is also required to run the example notebooks.

pip install opencv-python pycocotools matplotlib onnxruntime onnx ipykernel

More details can be found in install segment anything and install GroundingDINO

🏃 Run Grounding DINO Demo

Download the checkpoint for Grounding Dino:

cd Grounded-Segment-Anything

wget https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha/groundingdino_swint_ogc.pth

Run demo

export CUDA_VISIBLE_DEVICES=0
python grounding_dino_demo.py \
  --config GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py \
  --grounded_checkpoint groundingdino_swint_ogc.pth \
  --input_image assets/demo1.jpg \
  --output_dir "outputs" \
  --box_threshold 0.3 \
  --text_threshold 0.25 \
  --text_prompt "bear" \
  --device "cuda"

The model prediction visualization will be saved in output_dir as follow:

🏃‍♂️ Run Grounded-Segment-Anything Demo

Download the checkpoint for Segment Anything and Grounding Dino:

cd Grounded-Segment-Anything

wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth
wget https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha/groundingdino_swint_ogc.pth

Run Demo

export CUDA_VISIBLE_DEVICES=0
python grounded_sam_demo.py \
  --config GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py \
  --grounded_checkpoint groundingdino_swint_ogc.pth \
  --sam_checkpoint sam_vit_h_4b8939.pth \
  --input_image assets/demo1.jpg \
  --output_dir "outputs" \
  --box_threshold 0.3 \
  --text_threshold 0.25 \
  --text_prompt "bear" \
  --device "cuda"

The model prediction visualization will be saved in output_dir as follow:

⛷️ Run Grounded-Segment-Anything + Inpainting Demo

CUDA_VISIBLE_DEVICES=0
python grounded_sam_inpainting_demo.py \
  --config GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py \
  --grounded_checkpoint groundingdino_swint_ogc.pth \
  --sam_checkpoint sam_vit_h_4b8939.pth \
  --input_image assets/inpaint_demo.jpg \
  --output_dir "outputs" \
  --box_threshold 0.3 \
  --text_threshold 0.25 \
  --det_prompt "bench" \
  --inpaint_prompt "A sofa, high quality, detailed" \
  --device "cuda"

🏌️ Run Grounded-Segment-Anything + Inpainting Gradio APP

python gradio_app.py

The gradio_app visualization as follow:

🤖 Run Grounded-Segment-Anything + BLIP Demo

It is easy to generate pseudo labels automatically as follows:

Use BLIP (or other caption models) to generate a caption.
Extract tags from the caption. We use ChatGPT to handle the potential complicated sentences.
Use Grounded-Segment-Anything to generate the boxes and masks.

Run Demo

export CUDA_VISIBLE_DEVICES=0
python automatic_label_demo.py \
  --config GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py \
  --grounded_checkpoint groundingdino_swint_ogc.pth \
  --sam_checkpoint sam_vit_h_4b8939.pth \
  --input_image assets/demo3.jpg \
  --output_dir "outputs" \
  --openai_key your_openai_key \
  --box_threshold 0.25 \
  --text_threshold 0.2 \
  --iou_threshold 0.5 \
  --device "cuda"

The pseudo labels and model prediction visualization will be saved in output_dir as follows:

💘 Acknowledgements

Citation

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

@article{kirillov2023segany,
  title={Segment Anything}, 
  author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Doll{\'a}r, Piotr and Girshick, Ross},
  journal={arXiv:2304.02643},
  year={2023}
}

@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}
}

build an api based on fastapi

  python3 gsa_api.py

  api = "http://x.x.x.x:7590/gsa"
  {
        "pic_url": "http://p2.itc.cn/images01/20230404/7feb96302d264c008d4fd0e762c43387.jpeg",
        "task_type": "det",
        "text_prompt": "some people stand in the yard, everyone is dressed in chinese traditional dress and hold something",
        "box_threshold": 0.3,
        "text_threshold": 0.35
        }
  # 返回图片的base64
  res = requets.post(url=api, data=data).json()

  api = "http://x.x.x.x:7590/gsa?img=xxxxxx"
  # 返回检测后主体的bbox
  bbox = requets.post(url=api, data=data).json()

Here is my workaround to run the model without connecting to huggingface:

  Step 1: download necessary files listed in huggingface-bert-base-uncased, including config.json, flax_model.msgpack, pytorch_model.bin, tf_model.h5, tokenizer.json, tokenizer_config.json, vocab.txt
  Step 2: put downloaded files (Step 1) into your local folder. For example, the local folder could be Grounded-Segment-Anything/huggingface/bert-base-uncased
  Step 3: modify text_encoder_type in get_tokenlizer.py#L17
  and get_tokenlizer.py#L23 to your local folder (defined in Step 2)
  Step 4: run the model and enjoy it

LeanFly/Grounded-Segment-Anything-API