Compare2score

🚀 Compare2Score模型

Compare2Score模型可用于图像质量评估，通过特定的算法为图像给出质量评分，为图像质量的量化提供了有效的解决方案。

🚀 快速开始

使用AutoModel快速启动

可以使用transformers库中的AutoModel来快速启动模型。以下是一个示例代码，展示了如何使用AutoModelForCausalLM加载模型并对图像进行评分：

import requests
import torch
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("q-future/Compare2Score", trust_remote_code=True, attn_implementation="eager", 
                                             torch_dtype=torch.float16, device_map="auto")

from PIL import Image
image_path_url = "https://raw.githubusercontent.com/Q-Future/Q-Align/main/fig/singapore_flyer.jpg"
print("The quality score of this image is {}".format(model.score(image_path_url)))

在GitHub上进行评估

如果你想在本地对模型进行评估，可以按照以下步骤操作：

git clone https://github.com/Q-Future/Compare2Score.git
cd Compare2Score
pip install -e .

安装完成后，你可以使用以下代码对图像进行评分：

from q_align import Compare2Scorer
from PIL import Image

scorer = Compare2Scorer()
image_path = "figs/i04_03_4.bmp"
print("The quality score of this image is {}.".format(scorer(image_path)))

📚 引用

如果你使用了该模型，请引用以下论文：

@article{zhu2024adaptive,
  title={Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare},
  author={Zhu, Hanwei and Wu, Haoning and Li, Yixuan and Zhang, Zicheng and Chen, Baoliang and Zhu, Lingyu and Fang, Yuming and Zhai, Guangtao and Lin, Weisi and Wang, Shiqi},
  journal={arXiv preprint arXiv:2405.19298},
  year={2024},
}

📄 许可证

本项目采用MIT许可证。