I want to use our own noisy data to train the model

[kidd-f]

Thanks for your sharing! I have a question about which part of the code I should modify if I have my own different noisy picture.Because the training code is adding noise to the clean image.I want to train the model using my own nosiy image including real nosie.Hope to get your answer, I will be very grateful.

[yu4u]

Sorry, the purpose of this repo is to reproduce "the concept" of Noise2Noise thus it requires non trivial modifications to train real data.

[zhushuyun]

Can you tell me how to modify ?

!python3 "/content/noise2noise/train.py" \ --image_dir "/content/noise/target_noise" \ --image_noised_dir "/content/noise/source_noise" \ --test_dir "/content/noise/target_noise" \ --image_size 512 --batch_size 2 --lr 0.001 --model unet --target_noise_model clean --val_noise_model clean --output_path "/content/drive/MyDrive/noise2noise/clean/" \ #--weight "/content/drive/MyDrive/noise2noise/clean/weights.006-22.673-36.41483.hdf5"

noise2noise_real_data.zip

This is a quick change in the code, there may be bugs

Training result with 800 images