Joint-Bilateral-Learning icon indicating copy to clipboard operation
Joint-Bilateral-Learning copied to clipboard

style loss在relu1_1特征上计算了两次?

Open willer94 opened this issue 3 years ago • 1 comments

你好,非常感谢您的工作!在对比论文阅读您的代码时,我发现了在VGG.py中style loss好像有些问题,具体是在 loss(self, output, content, style, alpha=1.0)处计算了两次relu1_1特征的style loss

        loss_s = self.calc_style_loss(out_feats[0], style_feats[0])
        for i in range(0, 4):
            loss_s += self.calc_style_loss(out_feats[i], style_feats[i])

我反复阅读了论文,其中并没有提到要单独对relu1_1算两次loss,这里是怎么回事呢? 谢谢啦!

willer94 avatar Jan 30 '22 02:01 willer94

那应该是是复现的问题,改成range(1,4)把

mousecpn avatar Apr 13 '22 06:04 mousecpn