KAIR
KAIR copied to clipboard
cszn
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR
Thanks for this terrific repository! I'm confused about the configuration of patches when using the `blindsr` dataset type. The H and L patch sizes are extracted from the configuration here:...
Hey, I am trying to train the network with remote sensing data for super resolution. I am able to train the network using data parallel method, but when ever I...
您好，请问usrnet在SR inference的时候除了对退化核(如k1-k12)和噪声系数(如0-0.1)进行排列组合的尝试，还有什么更快或者更自动化的方法对退化核和噪声系数的组合进行筛选，从而针对该测试数据集(如一段视频等)达到最好的视觉效果？您的看法或者建议？
Thank you Kai Zhang. I have a question about training dpsr https://arxiv.org/pdf/2008.13751.pdf. About the optimization of eq. 6a and 6b, in the Algorithm 1, it seems that K iterations are...
Hello, I have some questions about training USRNet. When I read the training code, I can not find where the optimization of equation 5 and 6. In the lines 149-152...
Hi, First I'd like to congrat you about your great work! I'd like to ask whether a single precision training has been taken into consideration for the future, or if...
I want to get x2 pre_train model . so set the following parameters for training,one epoch cost time about 31s,some calculation,It takes a very long time to complete the training.my...
Hi, Can I use your pre-trained model to finetuning on my own dataset? I found in the JSON file for training that pretrained_netG and pretrained_netE are needed, but I don't...
Hello Sir, All files of this github site, It's much helpful to me. I want to predict of DRUNet using my datasets. BTW, I couldn't find test-code of DRUNet. Thanks,...
请问训练BSRGAN使用的数据量，patch_size，以及时间是多少； 我现在分为两步骤训练模型， 第一步骤使用的 python main_train_psnr.py --opt options/train_bsrgan_x4_psnr.json，差不多到480000iter， 第二步骤使用的 python main_train_gan.py --opt options/train_bsrgan_x4_gan.json，差不多到 330000iter， 测试第一步骤的结果发现超分结果没啥变化，已经趋向于稳定了，但测试第二步骤的超分模型时发现，iter仅仅相差5000，超分结果就非常不一样，请问这是因为使用 discriminator_unet 作为判别器的原因还是其他原因？ 突然发现 readme下面写的 使用的*_E.pth 比*_G.pth 稳定，而我使用的*_G.pth
