edge-connect
edge-connect copied to clipboard
knazeri
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212
Hello, I'm constantly facing this issue: I try to train whichever model avaiable and it immediatley stops right after it started. I set up environment which I guess should be...
It is a wonderful work. My question is Have you processed 202k images. I have used your model for 37790 images of celeba dataset. How many images you have tested?...
Here is what the paper describe. > With CelebA, we cropped the center **178x178** of the images, then resized them to 256x256 using bilinear interpolation. For Paris StreetView, since the...
python train.py --model 1 --checkpoints ./checkpoints/celebA Training epoch: 1 loading error: datasets/celebA/train/000195.jpg Traceback (most recent call last): File "E:\PycharmProject\edge-connect\src\dataset.py", line 41, in __getitem__ item = self.load_item(index) File "E:\PycharmProject\edge-connect\src\dataset.py", line 71,...
Thank you very much for your codes. I have trained the edge model for 2000,000 iterations, and get the following results  From my training, the model didn't generate satisfying...
Hello @knazeri Thanks for your opening source code. I have used your implementation to train from scratch. I stay all your settings unchanged, but only use another remote sensing dataset,...
RuntimeError: Error(s) in loading state_dict for EdgeGenerator: Missing key(s) in state_dict: "encoder.1.weight", "encoder.4.weight", "encoder.7.weight", "middle.0.conv_block.1.weight", "middle.0.conv_block.5.weight", "middle.1.conv_block.1.weight", "middle.1.conv_block.5.weight", "middle.2.conv_block.1.weight", "middle.2.conv_block.5.weight", "middle.3.conv_block.1.weight", "middle.3.conv_block.5.weight", "middle.4.conv_block.1.weight", "middle.4.conv_block.5.weight", "middle.5.conv_block.1.weight", "middle.5.conv_block.5.weight", "middle.6.conv_block.1.weight", "middle.6.conv_block.5.weight", "middle.7.conv_block.1.weight", "middle.7.conv_block.5.weight",...
Hi guys, Can we run the program directly on Colab? or we need some modifications? I appreciate your help.
Thank you for your excellent work. In your paper, you introduced how to get 256x256 images from original images on celebA and Paris StreetView. but for places2, how do you...
