ICT_DeepFake

ICT_DeepFake copied to clipboard

Can you share Training Code?

2

Thank you very much.

zhangyuereal

 this model should be renamed model_latest.pth,or you will have bad result.Lots of errors in this code.

ats4869

If i have my own dataset,how to put them in the correct path.I am a beginner.I need some tutorial to put dataset correctly

ats4869

I can't download the FF.zip file from Google Drive. Can anyone kindly provide another link, such as Baidu Cloud?

Yongzhang-Tan

Release Training Code

2

@LightDXY Thanks for the code. Please share the training code on GitHub or Email below. Best, [email protected]

ucalyptus2

Python 3.6  @LightDXY

ucalyptus2

ref

5

I have set the model_path,then run the eval.py,he gave me this error. the backbone model and the reference both in the folder.why he gave me this error? 

shui-tian-ju-shi

Just like written in the title, do you have any suggestions for threshold distance value for detecting in the wild datasets?? I was wondering if you have a optimum threshold...

DanLEE278

Hi, Xiaoyi, this is a remarkable work. Here, I want to ask about some question: **1. In table 1 of the paper, are the results of FFD and CNNDetect obtained...

MZMMSEC

I got the same issue(#7 ) when I want to run the ict_eval.py. It seems like there is sth wrong with my cuda compilation, leading to an importerror. I'm really...

3herry1in