train code with my own data

hezhangsprinter / DCPDN

Densely Connected Pyramid Dehazing Network (CVPR'2018)

401 stars 112 forks source link

train code with my own data #9

Closed dalianKJR closed 6 years ago

dalianKJR commented 6 years ago

Hello, I am reading your paper and try to run train code with my own data. but I don't know how to create haze image from ground truth, trans map and ato map. can you help me?

hezhangsprinter commented 6 years ago

All the syn samples (both training and testing) are strored in Hdf5 file. You can also generate your sample using 'create_train.py' (Please download the NYU-depth @ http://horatio.cs.nyu.edu/mit/silberman/nyu_depth_v2/nyu_depth_v2_labeled.mat)