Giter Club home page Giter Club logo

yenet-pytorch's People

Contributors

caenorst avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

yenet-pytorch's Issues

RuntimeError

when I run the program,I meet blow error:

RuntimeError :Expected 4-dimensional input for 4-dimensional weight [30,1,5,5],but got 5-
dimensional input of size [16,2,1,256,256] instead

I don't know why?please help me!

validation accuracy

Dear author
I'm using the BOSSbase_1.01 dataset, WOW algorithm 0.4bpp
4000 train, 1000 validation.
I train the model but I get valid_accuracy=0.5
could you help me what went wrong?

use_batch_norm

in train_loader, pair_constraint=not(args.use_batch_norm), Why set pair_constraint as False when use batch normalization?

In your implementation, the image don't be normalized to [0.0,1.0]?

DatasetNoPair

If the pair_constraint = false, the code will use DatasetNoPair. Like DatasetPair, the DatasetNoPair also can call transform (RandomRot, RandomFlip). In paired mode, the cover and stego images will be both rotated or flipped using the same setting.
However, when in no-pair mode, it can rotate or flip the cover image only, the corresponding stego image may not be rotated or flipped. Because the DatasetNoPair only load one image once.
Therefore, if set pair_constraint = false, the only transforms.Compose([
utils.ToTensor()
]) can be used?

how to rewrite it

the dataloaditer is out of date in pytorch1.0, how should I rewrite it or do something to instead? I use the dataloadFolder instead without pair, but the network seems didn't work.

Where is the part of incorporating the knowledge of selection-channel?

Dear author:
Thanks for your implementation about YeNet. However, I want to know whether your source code don't include the part of incorporating the knowledge of selection-channel? In other words. you have implemented TLU-CNN but not SCA-TLU-CNN. Is it right? Because I have found the embedding probability map is just used to generate the stego image (if embedding_otf=True). Would you mind sharing the updating code about implementing SCA-TLU-CNN?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.