House_Lee

@cszn 改成True后，提示以下错误 Traceback (most recent call last): File "main_test_rrdb.py", line 162, in main() File "main_test_rrdb.py", line 62, in main model.load_state_dict(torch.load(model_path), strict=True) File "/public_files/software/envs/mmsr/lib/python3.7/site-packages/torch/nn/modules/module.py", line 847, in load_state_dict self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError:...

同样卡了

同样的问题，请问解决没有

hi, I fix this error then has a new problem: File "E:/PycharmProjects/pytorch-cifar-master/main.py", line 18, in from utils import progress_bar File "E:\PycharmProjects\pytorch-cifar-master\utils.py", line 45, in _, term_width = os.popen('stty size', 'r').read().split()...

https://github.com/swz30/Restormer/blob/733ceb2e5cdab8074d59a8d440c645a11b5dd334/basicsr/data/paired_image_dataset.py#L207 把这一行的['gt_path']删了就可以

基于DF2K的paired数据进行训练，你可以根据readme构造自己的paired数据

这是[ESRGAN](https://github.com/xinntao/ESRGAN/)的预训练模型，可以在这里下载 [Download Link](https://drive.google.com/drive/u/0/folders/17VYV_SoZZesU6mbxz2dMAIccSSlqLecY)，但由于ESRGAN版本更新的原因，可能会存在某些权重参数加载失败的问题，你可以先试试

Thanks for your attentions. Please refer the Eq. 8 in paper, the real out is m_a*IRx+m_b*IRy. IRm is used to generate m_a. You can also found that in https://github.com/House-Leo/RWSR-EDL/blob/b8dda1ed10f210dd113cae219bdce224ad754aed/codes/models/modules/RRDBNet_arch.py#L96-L106 out1->IRx,...