dai-lab / rivagan Goto Github PK
View Code? Open in Web Editor NEWRobust video watermarking with non-differentiable adversaries.
License: MIT License
Robust video watermarking with non-differentiable adversaries.
License: MIT License
When I execute bash download.sh.
http://data.csail.mit.edu/soundnet/actions3/split1/Moments_in_Time_Mini.zip
The link looks invalid
What should I do and what links need to be replaced?
Paste the command(s) you ran and the output.
If there was a crash, please include the traceback here.
The extracted watermark information is a string of numbers of type Float32
How to check whether the extracted watermark is correct
part of outputs are like this
[array([-0.22932515, -0.05714366, -1.2726792 , -0.05257967, -0.10511999,
-4.496194 , -0.72906655, -7.0054197 , 1.2017044 , -0.07988264,
-0.554625 , -0.38207918, -0.37821755, -0.23825747, -0.06544079,
-0.18358664, -1.1621505 , -0.04027031, -1.3203971 , -0.04445288,
-0.02693273, -0.04580238, -0.09852732, -0.7537201 , -0.8482291 ,
-0.05759114, -0.9152253 , -0.15124811, -0.69108665, -1.4571815 ,
-0.08187085, -0.03920848], dtype=float32), array([-0.2196667 , -0.0540536 , -1.5967504 , -0.04509218, -0.10601447,
-3.8246827 , -0.8229772 , -7.316689 , 1.1962031 , -0.07542385,
-0.47025478, -0.42007202, 0.04247466, -0.1553794 , -0.05957376,
-0.12692125, -0.99911606, -0.01197424, -1.931857 , -0.04010678,
-0.0247244 , -0.04174514, -0.09097901, -1.3404232 , -0.8031849 ,
-0.05421488, -0.9168243 , -0.16437075, -0.63380903, -1.4590236 ,
-0.07584139, -0.0354542 ], dtype=float32), array([-0.21605897, -0.05655681, -1.5917764 , -0.04962874, -0.10279732,
-3.9548905 , -0.85447276, -6.641722 , 1.4988332 , -0.07171236,
-0.58976734, -0.4822218 , -0.5583661 , -0.44414252, -0.06283236,
-0.04334006, -0.9056364 , -0.02996331, -1.5311664 , -0.03888033,
-0.02365516, -0.04321809, -0.08855483, -1.3248276 , -0.70889914,
-0.0529329 , -0.914947 , -0.02763503, -0.58799237, -1.4167793 ,
-0.07745175, -0.03598158], dtype=float32), array([-0.21729237, -0.06073643, -1.7749408 , -0.05128128, -0.10150994,
-3.647244 , -0.9945726 , -6.587243 , 1.1882725 , -0.07274818,
-0.70474637, -0.2876239 , -0.6520075 , -0.2658491 , -0.06356473,
-0.10729884, -0.8362877 , -0.02482117, -1.4181769 , -0.03995933,
-0.02395962, -0.04428652, -0.09166634, -1.2472842 , -0.91013485,
-0.05398247, -0.73910624, -0.01726682, -0.67850876, -1.2625008 ,
-0.07508389, -0.03764728], dtype=float32), array([-0.21252002, -0.05803272, -2.0322752 , -0.05201769, -0.10255759,
-3.801908 , -0.960667 , -5.9786286 , 1.2340491 , -0.06969828,
-0.7945951 , -0.36546695, -1.2804725 , -0.16977169, -0.06502119,
0.04623017, -0.78163105, -0.01119128, -1.1249161 , -0.0384632 ,
-0.02465068, -0.04448389, -0.08820156, -1.0601249 , -0.8741142 ,
-0.05270627, -0.7521928 , 0.03751253, -0.57171124, -1.1868995 ,
-0.07276401, -0.03677569], dtype=float32), array([-0.22099555, -0.06090005, -1.6498708 , -0.05538905, -0.10977125,
-3.8797262 , -0.68402606, -6.6135855 , 1.1882415 , -0.07178833,
-0.7655401 , -0.5266853 , -0.8798227 , -0.19440982, -0.06883975,
0.03872593, -0.6610789 , -0.03265392, -1.6900032 , -0.0410734 ,
-0.02811369, -0.04813316, -0.09063462, -1.3307556 , -0.58502895,
-0.05466864, -0.6534804 , -0.21974505, -0.72906893, -1.1342072 ,
-0.07908204, -0.03858798], dtype=float32), array([-0.2232397 , -0.05757632, -1.4883542 , -0.04831245, -0.10195197,
-4.181132 , -0.581693 , -6.6753025 , 1.3174125 , -0.06622721,
-0.693849 , -0.54539883, -0.6668897 , -0.18836862, -0.06199639,
-0.03910651, -0.8918489 , -0.02746316, -1.9715004 , -0.03671256,
-0.02696823, -0.04149688, -0.08421695, -1.5544248 , -0.54859847,
-0.05067875, -0.60275084, -0.08506186, -0.6193348 , -1.1903898 ,
-0.07435871, -0.03601457], dtype=float32),
Hello, I would like to ask you how to set my training set. I put avi videos in the directory "data/Hollywood2", but when I was training, all the prompt "0it [00:00,? It /s]" appeared, and the value of each metric was NaN. How can I solve this problem?
Paste the command(s) you ran and the output.
If there was a crash, please include the traceback here.
Describe what you were trying to get done.
Tell us what happened, what went wrong, and what you expected to happen.
Paste the command(s) you ran and the output.
If there was a crash, please include the traceback here.
from rivagan import RivaGAN
model = RivaGAN()
model.fit('./data/hollywood2', epochs=300, batch_size=12, use_critic=True, use_adversary=True)
model.save('./checkpoints/model.pt')
When I use this script for training, I get a few warnings as follows,
[mp3float @ 0xe49f1240] Header missing
[mp3float @ 0xe49f1240] Header missing
[mp3float @ 0xe4c01e00] Header missing
I don't know if this affects the model.
My model accuracy has been stuck at about 54%.
What I use is Hollywood2 dataset and it has been processed for successful loading.
Has anyone else experienced the same problem, or has anyone reproduced the results of the paper.
the file script download.sh ,the path is not avaliable ftp://ftp.irisa.fr/local/vistas/actions/Hollywood2-actions.tar.gz ,where can get the resource
Can you provide the trained RivaGan model (.pt)?
Data folder is missing in root.
//downloaded instead of git clone...
Hi, I trained the model with hollywood2 according to the guideline. But I only get an accuracy of 74% when there is no modification. Did I miss anything? Thank you!
Li
In the Readme.md file displayed on the homepage: https://github.com/DAI-Lab/RivaGAN,
the URL for the documentation: https://dai-lab.github.io/RivaGAN is giving a "Page Not Found :(" message.
I was trying to encode watermark into video, Video output generates with a blue layer. Is there any solution or guide to resolve this?
Thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.