mango

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...

python3 iSeeBetterTest.py中如何设置参数，能够直接输入视频进行超分？

I don't understand this part of the test code，I think testing_data_loader is the test set data，only one image ,Why does batch have a lot of data，such as batch[0]、batch[1]....... code: for...

CUDA out of memory

3

when run python test.py --opt options/test/test_stage3.yml , input size (1920,1080,3),i want to get the image of size (3840,3160,3),print "CUDA out of memory"error,Is this a normal phenomenon? 

SMM block 可以用于超分的GAN网络 吗？

1

您好，请问该模块可以即插即用，应用在其他超分网络吗?

The model can be image denoised while SR, but in some scenarios, details are lost,has this happened during your test?for example original image  SR image  Tile texture features...

请问LPIPS指标如何计算？

1

在测试代码以及训练代码KAIA中，暂时没有找到该指标的计算方式，请问您是如何计算的？代码中有计算LPIPS的方法吗？

超分后图像尺寸问题

6

您好，按照您的测试流程测试test2K文件夹下的图片，x4超分，超分后的图像尺寸与HR尺寸不一致，如1299.png：   请问这种情况是什么原因呢？既然尺寸不一致，psnr指标如何计算的呢？

Hi,please,RAW image is dng format, can be directly used for training?How does the code read dng images?

about test data

2

when run ‘python test.py -d ./data -c ./NBNet_mge.pkl’，occur error ‘FileNotFoundError: [Errno 2] No such file or directory: './data/ValidationNoisyBlocksSrgb.mat'’,does the test dataset need a .mat file？