inpainting_gmcnn
inpainting_gmcnn copied to clipboard
shepnerd
Image Inpainting via Generative Multi-column Convolutional Neural Networks, NeurIPS2018
https://github.com/shepnerd/inpainting_gmcnn/blob/ba7f7109c38c3805800283cdb9d79cd7c4a3294f/tensorflow/net/network.py#L73 This line *seems* to be a bug (unless I'm missing something). Shouldn't this be `conv_3` instead of `conv_5`?
I pretrained the model with my own data about 10 epochs. and the result does not converge. then i want to try finetune step.but failed. any one can help me?...
Hi, is it possible to convert your trained pytorch or tensorflow model into coreml without implementing custom layer?
Hello, I think it's one of the best repos with inpainting!) But I have problems when I'm trying to do equal result.   Predicted img has artifacts will colored...
Hello, first of all thank you for your amazing work, as a student it has really helped me understanding GANs and how CNNs can do inpainting. After reading the paper...
after i run ：python test.py --dataset CelebA-HQ_256 --data_file ./imgs/celebahq_25 6x256/ --load_model_dir ./checkpoints/10_net_GM.pth --random_mask 0 mistakes happened：python test.py --dataset CelebA-HQ_256 --data_file ./imgs/celebahq_25 6x256/ --load_model_dir ./checkpoints/10_net_GM.pth --random_mask 0 why？？？
Thank you for sharing your code. I am wandering weather the code supporting multi-gpu training? It seems that simply add `ourModel = torch.nn.DataParallel(ourModel).cuda()` in train.py brings about errors.
Greetings! I change the input image size from 256,256,3 to 128,128,3, and mask size from 128,128 to 64,64 in the pytorch implementation. However, there seem to be hard-coded padding in...
Greetings! Thank you for your excellent work. I have come across three problems and hope that you or the github community can provide me some insights. 1. I downloaded the...
Hi~ I am training on my own dataset. In stage 2, I get this image(up to down: GT, image feed to the generator, result)  As you can see, a...
