Closed llmpass closed 2 years ago
Both put the original SIDD GT/Noisy images and Crop your own patches are OK here. We will randomly crop patches in our dataset. Cropping patches as input is just to speed up the loading of data.
Both put the original SIDD GT/Noisy images and Crop your own patches are OK here. We will randomly crop patches in our dataset. Cropping patches as input is just to speed up the loading of data.
Thank you!
In the yaml file, 2 folders have to be set:
Show I put original SIDD GT and noisy png files into these folders or show I run your crop_sidd.py to create a large number of cropped images? In addition, what should be the file names in those folders?