- Notifications
You must be signed in to change notification settings - Fork13
HiDDeN: Hiding Data with Deep Networks.
License
NotificationsYou must be signed in to change notification settings
jirenz/HiDDeN
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
HiDDeN: Hiding Data with Deep Networks.arxiv ECCV 2018
Jiren Zhu*, Russell Kaplan*, Justin Johnson, Li Fei-Fei
*: These authors contributed equally
Warning: This repo is still WIP, let us know if you encounter bugs or issues.
A sample dataset is provided indata/yuv_coco_debug.t7. Afte you download train2014 of COCO dataset, you can useHiDDeN/coco_prep.lua to generate the training dataset.
- With the testing dataset. You can run
th main.lua --develop --name test-run --type float, training results will be written tocheckpoints/test-run.
- If you have cuda setup. You can run
th main.lua --develop --name <experiment name>instead, as--type cuda is default.
If you have the full dataset, remove thedevelop flag.
Coming soon...
- Pytorch implementation by Ando Khachatryan:https://github.com/ando-khachatryan/HiDDeN.