SCUNet
SCUNet copied to clipboard
Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis (Machine Intelligence Research 2023)
pth转为onnx,由于mul操作不支持矩阵于矩阵相乘的动态尺寸,不知道作者是否有尝试过导出动态尺寸的onnx模型成功推理嘛?
it was found that ‘scunet_color_real_gan.pth’ will cause a change in image brightness Is there any solution?
It is a nice work. And I am wonder do you have any plans to release the code for training data synthesis?
SCUNetG is based on SCUNet checkpoint? thanks
When will the pre-training weights of imagenet be announced?
Hi, when will the training code be released? What is the size of your training image?
Hi I am using 8-bit greyscale as input, and note the usual `/255` operations to put data in the range `0-1`. However the operation ``` if args.need_degradation: # degradation process...
run code of "python main_download_pretrained_models.py --models "SCUNet" --model_dir "model_zoo" " , i get the traceback requests.exceptions.SSLError: HTTPSConnectionPool(host='github.com', port=443): Max retries exceeded with url: /cszn/KAIR/releases/download/v1.0/scunet_gray_15.pth (Caused by SSLError(SSLZeroReturnError(6, 'TLS/SSL connection has...
I am getting the following error, while trying to convert the pre-trained model to ONNX model. Can you please look into it and let me know that the pre-trained weights...