https://github.com/shizenglin/training-free-object-counter

https://github.com/shizenglin/training-free-object-counter

Last synced: about 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/shizenglin/training-free-object-counter
• Owner: shizenglin
• Created: 2023-06-30T05:18:03.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-12-14T05:17:46.000Z (about 1 year ago)
• Last Synced: 2023-12-14T06:24:30.094Z (about 1 year ago)
• Language: Python
• Size: 4.53 MB
• Stars: 21
• Watchers: 2
• Forks: 1
• Open Issues: 4
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Segment-Anything - [code

README

        


Training-free Object Counting with Prompts authored by Zenglin Shi, Ying Sun, Mengmi Zhang. [pdf] [poster] [video] 

 Installation 

1. The code requires python>=3.8, as well as pytorch>=1.7 and torchvision>=0.8. 


2. Please follow the instructions here to install both PyTorch and TorchVision dependencies. 


3. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.


 Getting Started 

1. Download the 'vit_b' pre-trained model of SAM and save it to the folder 'pretrain'. 


2. Download the FSC-147 and CARPK datasets and save them to the folder 'dataset' 


3. Run 


```

python main-fsc147.py --test-split='test' --prompt-type='box' --device='cuda:0'

```

or

```

python main-carpk.py --test-split='test' --prompt-type='box' --device='cuda:0'

```

 Success and failure results 



 Acknowledgment 

We express our sincere gratitude to the brilliant minds behind SAM, Personalize-SAM and CLIP-Surgery, as our code builds upon theirs. 


 Citing 

If you use our code in your research, please use the following BibTeX entry.


  ```

  @inproceedings{Shi2023promptcounting,

    title={Training-free Object Counting with Prompts},

    author={Zenglin Shi, Ying Sun, Mengmi Zhang},

    booktitle={WACV},

    year={2024}

  }

 ```