| import spaces | |
| import pyiqa | |
| import torch | |
| class IQA: | |
| def __init__(self, model_name="nima"): | |
| device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu") | |
| self.model = pyiqa.create_metric(model_name, device=device) | |
| print(self.model) | |
| def __call__(self, image_path): | |
| return self.model(image_path) | |
| if __name__ == "__main__": | |
| import requests | |
| from PIL import Image | |
| import glob | |
| image_files = glob.glob("samples/*") | |
| iqa_metric = IQA(model_name="nima-vgg16-ava") | |
| for image_file in image_files: | |
| print(image_file) | |
| image = Image.open(image_file) | |
| score = iqa_metric(image) | |
| print(score) |