Chaofeng Chen

Hi there, thank you so much for your detailed feedback and thorough analysis! I'm glad to hear that IQA-PyTorch is proving useful in your model evaluation process. I’d be happy...

You're welcome! I'm glad to hear that you found the explanations helpful. Regarding `ckdn`, I apologize for any confusion in my previous explanation. `ckdn` is a unique type of IQA...

请参考 #160。考虑到数据集的质量问题，我们推荐训练测试的配置为[Performance Evaluation Protocol](https://github.com/chaofengc/IQA-PyTorch/tree/main?tab=readme-ov-file#performance-evaluation-protocol)。 如果需要对应的数据集的结果，请自行参考样例写配置文件。

`brisque` 不是神经网络模型，不能用`torch.load_state_dict`。你可以尝试`model_BRISQUE = pyiqa.create_metric('brisque', device=device, pretrained_model_path=[your/local/weight/path])`

警告信息不影响实际使用。 初次加载的速度问题可能是受到 load 权重的影响，后续尝试解决

已在最新的commit中处理 6edfb07