search

HongguLiu / Deepfake-Detection

The Pytorch implemention of Deepfake Detection based on Faceforensics++
https://github.com/ondyari/FaceForensics
Apache License 2.0
293 stars 57 forks source link

About training. #15

Open hirusnov opened 3 years ago

hirusnov commented 3 years ago

How many times do you train to get the best results? Can I use the old pre-trained model to continue train new models?

HongguLiu commented 3 years ago
  1. We usually train our model in 50-100 epochs.
  2. Of course, you can use the pretraiend model and finetune for your task.
hirusnov commented 3 years ago

Ohhhh, I saw you use 40 videos original and 40 videos deepfake with 50 100 epochs, is it right?

HongguLiu commented 3 years ago

We use 720 videos and 140 videos to train and validate, and we randomly extract 50 frames for each video.

hirusnov commented 3 years ago

Okayyy, thank you so much. I understand