update

README.md

@@ -1,2 +1,50 @@
-# deepfake
+# Deepfake
 
+*author: Zhuoran Yu*
+
+<br />
+
+## 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](https://github.com/smu-ivpl/DeepfakeDetection).
+
+<br />
+
+## Code Example
+
+Load videos from path '/home/test_video'
+and use deepfake operator to predict the probabilities of fake videos.
+
+
+```python
+from towhee import ops
+deepfake = ops.deepfake()
+pred = deepfake('/home/test_video')
+print(pred)
+```
+
+<img src="./deepfake.png" height="100px"/>
+
+```shell
+[0.9893, 0.9097]
+```
+
+<br />
+
+## 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.

deepfake.py

@@ -60,7 +60,7 @@ class Deepfake(NNOperator):
 '''
 if __name__ == "__main__":
     filepath = "/home/xuyu/Deepfake/deepfake_detec/"
-    op = Deepfakevit()
+    op = Deepfake()
     pred = op(filepath=filepath)
     print(pred)
 '''

requirements.txt

@@ -0,0 +1,9 @@
+dlib
+facenet-pytorch
+albumentations
+timm
+pytorch_toolbelt 
+tensorboardxython 
+matplotlib 
+tqdm 
+pandas