Self-restrained-Triplet-Loss icon indicating copy to clipboard operation
Self-restrained-Triplet-Loss copied to clipboard

traing dataset

Open 4ff4n opened this issue 2 years ago • 1 comments

hello there! thank you so much for sharing your amazing work. would you please assist me how can i prepare my own custom dataset and what should the the directory structure in order to call the main.py to start the training process?

thanks Affan

4ff4n avatar May 09 '22 05:05 4ff4n

You should create one folder (e.g. id1, id2.....idn) for each identity in your dataset. Inside each folder, you should create two folders original (embedding of unmasked images)and fakemask (embedding of masked images)

fdbtrs avatar Sep 16 '22 12:09 fdbtrs