search

Reyhanehne / CVF-SID_PyTorch

Official implementation of the paper "CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Image" (CVPR 2022)
70 stars 11 forks source link

If I want to train on our own dataset #5

Open royaljava opened 1 year ago

royaljava commented 1 year ago

HI！If I want to train on our own dataset，and how should I prepare data， such as ‘Scene_Instances.txt’

myavartanoo commented 1 year ago

Thank you very much for your question. self.Validation_Gt and self.Validation_Noisy are the list of GT clean and input noisy images, respectively. Therefore, you can simply load your list of images and edit the lines 41 and 42 of the CVF-SID_PyTorch/src/data_loader/data.py . Please not that, line 40 reads the names of images so you can replace it with the name list of your images.

lulu-165 commented 1 year ago

May I ask if i need images in .png format during the test, or do i only need a .mat file?

myavartanoo commented 1 year ago

You can edit lines 41 and 42 of the CVF-SID_PyTorch/src/data_loader/data.py to read your images as a list of .png files or a .mat file.

lulu-165 commented 1 year ago

When I tested, I read ValidationGtBlocksSrgb.mat and ValidationNoisyBlocksSrgb.mat according to the readme, but there is no content in output/C, output/GT, output/I, output/N_d, output/N_i, what is going on?

lulu-165 commented 1 year ago

image like this.

code-8888 commented 1 year ago

image喜欢这个。

hello 你这个是怎么跑起来的 为什么我报错呢

PS E:\githubProjects\CVF-SID_PyTorch\src> python test.py --device 0 --config ../models/CVF_SID/SIDD_Val/config.json --resume ../models/CVF_SID/SIDD_Val/model_best.pth
Traceback (most recent call last):
  File "test.py", line 11, in <module>
    from torch.distributed.optim import DistributedOptimizer
  File "D:\python3.8\lib\site-packages\torch\distributed\optim\__init__.py", line 8, in <module>
    from .optimizer import DistributedOptimizer
  File "D:\python3.8\lib\site-packages\torch\distributed\optim\optimizer.py", line 8, in <module>
    from torch.distributed.rpc import RRef
ImportError: cannot import name 'RRef' from 'torch.distributed.rpc' (D:\python3.8\lib\site-packages\torch\distributed\rpc\__init__.py)