|
import torch
|
|
import torch.nn.functional as F
|
|
from PIL import Image
|
|
from facenet_pytorch import MTCNN
|
|
from transformers import Pipeline
|
|
|
|
|
|
class DeepFakePipeline(Pipeline):
|
|
def __init__(self, **kwargs):
|
|
Pipeline.__init__(self, **kwargs)
|
|
|
|
def _sanitize_parameters(self, **kwargs):
|
|
return {}, {}, {}
|
|
|
|
def preprocess(self, inputs):
|
|
return inputs
|
|
|
|
def _forward(self, input):
|
|
return input
|
|
|
|
def postprocess(self, confidences):
|
|
out = {"confidences": confidences}
|
|
return out
|
|
|
|
def predict(self, input_image: Image.Image):
|
|
DEVICE = 'cuda:0' if torch.cuda.is_available() else 'cpu'
|
|
mtcnn = MTCNN(
|
|
select_largest=False,
|
|
post_process=False,
|
|
device=DEVICE)
|
|
mtcnn.to(DEVICE)
|
|
model = self.model.model
|
|
model.to(DEVICE)
|
|
|
|
face = mtcnn(input_image)
|
|
if face is None:
|
|
raise Exception('No face detected')
|
|
|
|
face = face.unsqueeze(0)
|
|
face = F.interpolate(face, size=(256, 256), mode='bilinear', align_corners=False)
|
|
face = face.to(DEVICE)
|
|
face = face.to(torch.float32)
|
|
face = face / 255.0
|
|
|
|
with torch.no_grad():
|
|
output = torch.sigmoid(model(face).squeeze(0))
|
|
real_prediction = 1 - output.item()
|
|
fake_prediction = output.item()
|
|
confidences = {
|
|
'real': real_prediction,
|
|
'fake': fake_prediction
|
|
}
|
|
return self.postprocess(confidences)
|
|
|
