Official repository of "DeepMIH: Deep Invertible Network for Multiple Image Hiding", TPAMI 2022.
This repo is the official code for
Published on IEEE Transactions of Pattern Analysis and Machine Intelligence (TPAMI 2022). @ Beihang University.
config.py
:line50: TRAIN_PATH_DIV2K = ''
line51: VAL_PATH_DIV2K = ''
line54: VAL_PATH_COCO = ''
line55: TEST_PATH_COCO = ''
line57: VAL_PATH_IMAGENET = ''
MODEL_PATH
and the file name suffix
before testing by the trained model.model_checkpoint_03000_1.pt
, model_checkpoint_03000_2.pt
, model_checkpoint_03000_3.pt
,/home/usrname/DeepMIH/model/
,PRETRAIN_PATH = '/home/usrname/DeepMIH/model/'
,PRETRAIN_PATH_3 = '/home/usrname/DeepMIH/model/'
,suffix = 'model_checkpoint_03000'
.TEST_PATH
.test_oldversion.py
.MODEL_PATH
.config.py
is correct. Make sure the sub-model(net1, net2, net3...) you want to train is correct.train_old_version.py
. Following the Algorithm 1 to train the model.In the train_old_version.py
at line 223:
rev_secret_dwt_2 = rev_dwt_2.narrow(1, 4 * c.channels_in, 4 * c.channels_in) # channels = 12
,
the recovered secret image_2 is obtained by spliting the middle 12 channels of the varible rev_dwt_2
. However, in the forward process_2, the input is obtained by concatenating (stego, imp, secret_2) together. This means that the original code train_old_version.py
has a bug on recovery process (the last 12 channels of the varible rev_dwt_2
should be splited to be the recovered secret image_2, instead of the middle 12 one). We found that in this way the network is still able to converge, thus we keep this setting in the test process.
We also offer a corrected version train.py
(see line 225) and test.py
. You can also train your own model in this way.
Feel free to contact: [email protected].
If you find this repository helpful, you may cite:
@ARTICLE{9676416,
author={Guan, Zhenyu and Jing, Junpeng and Deng, Xin and Xu, Mai and Jiang, Lai and Zhang, Zhou and Li, Yipeng},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={DeepMIH: Deep Invertible Network for Multiple Image Hiding},
year={2022},
volume={},
number={},
pages={1-1},
doi={10.1109/TPAMI.2022.3141725}}