Deepfake

author: Zhuoran Yu

Description

Deepfake techniques, which present realistic AI-generated videos of people doing and saying fictional things, have the potential to have a significant impact on how people determine the legitimacy of information presented online.

This operator predicts the probability of a fake video for a given video.This is an adaptation from DeepfakeDetection.

Code Example

Load videos from path '/home/test_video' and use deepfake operator to predict the probabilities of fake videos.

from towhee.dc2 import pipe, ops, DataCollection

p = (
    pipe.input('path')
        .map('path', 'scores', ops.towhee.deepfake)
        .output('scores')
)

DataCollection(p('./deepfake_video/test/aagfhgtpmv.mp4').get_dict()).show()

[0.99]

Interface

A deepfake operator takes videos' paths as input. It predicts the probabilities of fake videos.The higher the score, the higher the probability of it being a fake video.(It can be considered to be a fake video with score higher than 0.5)

Parameters:

filepath: str

Absolute address of the test videos.

Returns: list

The probabilities of videos being fake ones.