search

knazeri / edge-connect

EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212
http://openaccess.thecvf.com/content_ICCVW_2019/html/AIM/Nazeri_EdgeConnect_Structure_Guided_Image_Inpainting_using_Edge_Prediction_ICCVW_2019_paper.html
Other
2.5k stars 530 forks source link

I doubt if the input data I trained is not a problem？ #107

Open 695874419 opened 5 years ago

695874419 commented 5 years ago

The forward method of InpaintingModel is as follows： def forward(self, images, edges, masks): images_masked = (images * (1 - masks).float()) + masks inputs = torch.cat((images_masked, edges), dim=1) outputs = self.generator(inputs) return outputs I visualized the variables about the image. As shown below： image I think there is a problem with my images_masked variable. Is this input correct?

anshen666 commented 4 years ago

你好，我最近也在跑这个代码。可以加你交流一下吗？我的微信：loveanshen 我的QQ：519838354 我的邮箱：519838354@qq.com 非常期待你百忙中的回复