目前最好的二姐，第10样本学习LOSS=0.0998,成图由384X768画面放大1.5倍，upscaler R-ESRGAN 4X+到576X1152（能整除64，效果最好）。
At present, the best second sister, the 10th sample learning loss=0.0998, zoomed in by 1.5 times from 384X768, upscaler R-ESRGAN 4X+to 576X1152 (can divide by 64, the best effect).
目前最好的二姐，第10样本学习LOSS=0.0998,成图由384X768画面放大1.5倍，upscaler R-ESRGAN 4X+到576X1152（能整除64，效果最好）。
At present, the best second sister, the 10th sample learning loss=0.0998, zoomed in by 1.5 times from 384X768, upscaler R-ESRGAN 4X+to 576X1152 (can divide by 64, the best effect).