search

cszn / DnCNN

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)
https://cszn.github.io/
1.42k stars 534 forks source link

If I want to input my own image for deep learning,but i don't need add to Gassian noise level,what should I do? #94

Open LIN-CHENG-YUEH opened 2 years ago

LIN-CHENG-YUEH commented 2 years ago

Sorry to disturb everyone during your busy schedule. I am a student,,I recently taught myself deep learning and machine vision in my spare time outside of work.

If I want to input my own image for deep learning,but i don't need add to Gassian noise level,what should I do?

If I want to test the operation of the program,I download DnCNN and run "GenerateTrainingPatches" program of "DnCNN_TrainingCodes_v1.1" file and "Demo_Train_model_64_25_Res_Bnorm_Adam" program of "DnCNN_TrainingCodes_v1.1". I want to ask what to do next?which program do i need to run.

And I run "GenerateData_model_64_25_Res_Bnorm_Adam" program of "DnCNN_TrainingCodes_v1.0" and "Demo_Train_model_64_25_Res_Bnorm_Adam" program of "DnCNN_TrainingCodes_v1.0",but MATLAB as shown in the attached. DnCNN_TrainingCodes_v1 0-error1 This problem has been bugging me for weeks,I have searched the internet for answers but to no avail.Hope someone can assist me. I only know MATLAB now,but I can try to understand other programming languages.

Thanks eveyone

john-yyb commented 4 months ago

I think you just need to change the noise in the dataset to the LQ you want to enter. And you also add noise to it