Effort 指标评估模型 load 失败

[Zhangyr2022]

感谢贵团队的高质量工作。我在使用 Effort 代码评估时遇到了如下错误：

Traceback (most recent call last):
  File "/mnt/data/home/zyr/RealGen-main/eval/model-eval/eval/effort_eval.py", line 390, in <module>
    main()
  File "/mnt/data/home/zyr/RealGen-main/eval/model-eval/eval/effort_eval.py", line 358, in main
    scorer = EffortScorer(
  File "/mnt/data/home/zyr/RealGen-main/eval/model-eval/eval/effort_eval.py", line 340, in __init__
    self.model.load_state_dict(new_weights, strict=False)
  File "/mnt/data/envs/Miniconda3/envs/bagel/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2584, in load_state_dict
    raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for EffortDetector:
        size mismatch for backbone.embeddings.position_embedding.weight: copying a param with shape torch.Size([257, 1024]) from checkpoint, the shape in current model is torch.Size([577, 1024]).

我下载的 effort 模型是参考仓库 https://github.com/YZY-stack/Effort-AIGI-Detection/tree/main#2-download-checkpoints 下的模型，下载了 genimage 和 chameleon 训练的模型，但是都遇到上述问题。请问该问题可以怎么解决呢？非常感谢🙏