liuqk3 / PUT

Paper 'Transformer based Pluralistic Image Completion with Reduced Information Loss' in TPAMI 2024 and 'Reduce Information Loss in Transformers for Pluralistic Image Inpainting' in CVPR2022
MIT License
169 stars 14 forks source link

关于推理时的问题 #37

Open zhoushijie28 opened 1 month ago

zhoushijie28 commented 1 month ago

作者您好,我在以inference_inpainting运行inference.py时报错torch.nn.modules.module.ModuleAttributeError: 'PatchVQGAN' object has no attribute 'generate_content',我在patch_vqgan.py中也确实没有找到generate_content,想请教一下您对这个问题的看法,谢谢!

liuqk3 commented 1 month ago

感谢关注我们的工作。这个错误应该是测试命令不对,请参考inference_commands_tpami2024.sh的示例进行测试。