import torch
from PIL import Image
from model import CycleReward

device='cuda'
model = CycleReward.from_pretrained("carolineec/CycleReward-I2T")
model.to(device)
model.eval()

preprocess = model.preprocess
image_path = "cat.jpg"
caption = "a photo of a cat"
image = preprocess(Image.open(image_path)).unsqueeze(0).to(device)
print('prepared data')

score = model.score(image, caption) 
print('my score:', score.item())

@article{bahng2025cyclereward,
title={Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences},
author= {Bahng, Hyojin and Chan, Caroline and Durand, Fredo and Isola, Phillip},
journal={arXiv preprint arXiv:2506.02095},
year={2025}
}