search

haimengzhao / CAE-ADMM

CAE-ADMM: Implicit Bitrate Optimization via ADMM-Based Pruning in Compressive Autoencoders
https://arxiv.org/abs/1901.07196
MIT License
46 stars 9 forks source link

DATASET #3

Closed lzzlxxlsz closed 4 years ago

lzzlxxlsz commented 4 years ago

what should I do if I want to use my own dataset ?

haimengzhao commented 4 years ago

Hi, thanks for your interest in our work. If you want to change the training set, simply change the --dataset_path argument when calling train.py. If you want to change the test set, you should first modify the parameters representing the height and width in utils.py/Kodak and save_kodak_img to be in line with your own dataset since it involves the decomposing and composing of patches. Then you should change the --testset_path argument when calling train.py.