Donggeun Ko
Donggeun Ko
Hello Prof. Zhu. I have a question for the paper. If we do not have color image (ground truth) during inference, is it impossible to provide local/global hint (patches that...
Good evening authors (in Asia :)) ! I am interested in your beautiful work and I want to try it on a custom data (input and generated synthetic image). However,...
Hello sir. I would like to use omnianomaly on training with other dataset such as SWaT and WADI. Is it possible to train on SWaT? If yes, which part of...
First of all, thank you for the great work. I have 2 questions. 1. I was training the model in my custom dataset and the training seems to be going...
Hello there! I was looking at VGG16 with CBAM. From the forward function, I see the following lines of codes ``` def forward(self,x): x = self.features_1(x) scale = torch.nn.functional.sigmoid(self.max_pool_1(x) +...
Hello! I am having problem with create_synthetic_dataset.py. It seems that the code underlined in red is not working. When I intersect ea with eb and print(mp) the print message is...
Hello authors! I have question regards to the paper itself. I ain't sure if this is the right place to ask. Figure 1 seems to be the training mechanism. However,...
Hello, Why is ur dataset composed of txt files not image files? Can you use image files (ex. FF++ c40 DF,F2F..) as an input instead of txt files?