When I use "python faceswap.py train (...)", are the model weights randomly initialized? Or are they pre-trained? If so, in which dataset? Imagenet?
Autoencoder model weights
Read the FAQs and search the forum before posting a new topic.
This forum is for discussing tips and understanding the process involved with Training a Faceswap model.
If you have found a bug are having issues with the Training process not working, then you should post in the Training Support forum.
Please mark any answers that fixed your problems so others can find the solutions.
- leommiranda
- Posts: 1
- Joined: Thu Oct 15, 2020 4:45 pm
- Has thanked: 1 time
Re: Autoencoder model weights
They are not pre-trained.
There are various options for initialization (ICNR and Convolutional-Aware) which can be used, otherwise the are generally initialized with He Uniform distribution.
My word is final