search

SeungjunNah / DeepDeblur_release

Deep Multi-scale CNN for Dynamic Scene Deblurring
679 stars 142 forks source link

Training with a different dataset #20

Closed bionictoucan closed 6 years ago

bionictoucan commented 6 years ago

Hi Seungjun, I am currently trying to train the network with a different dataset than the GoPRO to help deblur the images I am using. I'm having a problem in getting the code to recognise my dataset though. I currently have my images saved in DeepDeblur_release/dataset/TrainingPairs/train/1/ then I have the images split into blur and sharp like the GOPRO dataset. When training the model I change the dataset option to be "TrainingPairs" and expected everything else to work fine due to the same layers of directories etc. being used as the GoPRO dataset.

However, in running this, I receive the error "/home/armstrong/DeepDeblur_release/code/donkey.lua:138: attempt to get length of global 'train_list' (a nil value)". This seems to imply that it cannot find the data I am trying to train with. I was wondering if there is something off about how I am structuring the path to my training data? I hope you can help.

Kind regards, John Armstrong

SeungjunNah commented 6 years ago

Hi John,

The source code looks into different locations with optional arguments, 'dataset' and 'blur_type.' By default, it assumes the GoPro dataset and 'gamma2.2' synthesized blur images. Had you typed th main.lua -dataset TrainingPairs, an example of blur directory should be:

DeepDeblur_release/dataset/TrainingPairs/train/1/blur_gamma

Then it wouldn't find any data on that location since your blur data is on

DeepDeblur_release/dataset/TrainingPairs/train/1/blur

You can run the source code by modifying input arguments as:

th main.lua -dataset TrainingPairs -blur_type linear

Please take a look at opts.lua line 27 and data.lua line 29-77.

bionictoucan commented 6 years ago

Hi Seungjun,

Thank you very much! Problem solved.

Best wishes, John