DeblurGAN
DeblurGAN copied to clipboard
KupynOrest
Image Deblurring using Generative Adversarial Networks
Hi @KupynOrest , thanks for releasing your code for both training and test. In the tesing stage, "--resize_or_crop" flag will be set to "resize_or_crop" by default, thus the input testing...
When using default NLayerDiscriminator(input_nc=3, ndf=64, n_layers=3, norm_layer=nn.BatchNorm2d, use_sigmoid=False, gpu_ids=[], use_parallel=True), the provided latest_net_D.pth cannot fit the Discriminator. RuntimeError: Error(s) in loading state_dict for NLayerDiscriminator: Missing key(s) in state_dict: "model.3.weight", "model.3.bias",...
Thanks for sharing the code. And i have a question: how many images are suitable for the training , cause i randomly cropped 2500 images from GoPro Data set for...
Hello, I want to use DeblurGAN for grey images, so I change the input_nc and output_nc to 1, and add codes to both A_img and B_img: .convert("L"). But there are...
I keep the Generator weights provided in the file and run the model. When I use the test photo chosen from the go pro dataset, or put it another way,...
I want to use my model ,then I make the real picture folder and the corresponding fake pictures folder I run the command （python datasets/combine_A_and_B.py --fold_A /path/to/data/A --fold_B /path/to/data/B --fold_AB...
Good evening! I'm getting an error in the Visualizer(opt) function, which states that module 'requests' has no attribute 'Session'. Any idea what might be causing this? Many thanks! 
I picked 1500 images whose size is 640x480 from the MS COCO dataset, and tried to train a new model. When I tested the model, I found the Checkerboard Artifacts...
I am very sorry to bother you. I would like to ask how the datasets organize their own training data paths. What data is stored in each folder?
Metadata
Owner
Metadata
Image Deblurring using Generative Adversarial Networks