请问该模型可以用于中文文本图像的超分辨率吗？

[Lebron-Harden]

[RRRROBOT]

hxd， 要是找到了麻烦艾特我一下 我最近也在看这个

[NineMeowICT]

如果你说的是用所提供数据集训练的权重，那不行，论文里写了： In the future, we will capture more appropriately distributed text images. Extremely large and small images will be avoided. The images should also contain more kinds of languages, such as Chinese, French and Germany. We will also focus on new methods such as introducing recognition attention into the text super-resolution task. 该数据集里是没有汉字的 但是既然给出了训练脚本，如果有合适的汉字数据集，可以自己训练，这个架构的训练硬件需求应该不会太过高