jonasricker / diffusion-model-deepfake-detection Goto Github PK

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?

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 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,

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?

when the image is jpg,can it run?

Hi jonasricker!
I wonder if the generated face dataset is included in the dataset you provided.

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)