jonasricker / diffusion-model-deepfake-detection Goto Github PK
View Code? Open in Web Editor NEW[VISAPP2024] Towards the Detection of Diffusion Model Deepfakes
Home Page: https://arxiv.org/abs/2210.14571
License: MIT License
[VISAPP2024] Towards the Detection of Diffusion Model Deepfakes
Home Page: https://arxiv.org/abs/2210.14571
License: MIT License
when the image is jpg,can it run?
Hello there!
I have a problem running yours scripts because I have Macbook with Intel Chip so I cannot install torch with CUDA )))) So scrips falls with following error:
AssertionError: Torch not compiled with CUDA enabled
is there any simple way to run scripts on cpu? maybe it's very simple, but i'm new to nn and python, so i can't find easy way to do it
Thanks)
Hi jonasricker
I want to test your model and get your result but i have a problem with packages that code need.
Can you tell me version of each package you used?
I will be grateful.
Hi,
thanks for providing the useful code. https://github.com/jonasricker/diffusion-model-deepfake-detection/tree/main/detectors
I am wondering if you provide your own trained weights on Diffusion Datasets or if these weights are the original one?
Hi,
I have been in the process of downloading all the images from the zenodo link and I wanted to create a folder of 50k items for each of the models, so I can use them for my own experiments. However, I have noticed that LDM and PNDM only have 40k samples in total after combining all folders. I suspect this might be due to the train zip only containing 29k samples for LDM and PNDM, but I cannot say this for sure, as I do not have access to that zip anymore and downloading it again will take a long time.
Is this true or is it a mistake on my part?
seaborn._oldcore is unavailable anymore, so it reports the above error.
I suggest changing the code of line 107-108 in the file " src/paper_utils.py" to "dashes = ["-"]*len(sns.color_palette("deep"))".
Hi jonasricker!
I wonder if the generated face dataset is included in the dataset you provided.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.