search

Yang-Liu1082 / InvDN

Implementation for the paper: Invertible Denoising Network: A Light Solution for Real Noise Removal (CVPR2021).
Apache License 2.0
185 stars 35 forks source link

How to set the training folders (format) #11

Closed llmpass closed 2 years ago

llmpass commented 2 years ago

In the yaml file, 2 folders have to be set:

dataroot_GT: '' # path to training Clean images
dataroot_Noisy: '' # path to training Noisy images

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?

Yang-Liu1082 commented 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.

llmpass commented 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.

Thank you!