search

neuralchen / SimSwap

An arbitrary face-swapping framework on images and videos with one single trained model!
Other
4.46k stars 883 forks source link

Is model.netArc defined in your released version? #298

Open B-1368 opened 2 years ago

B-1368 commented 2 years ago

In the training process, we will only get net_G and net_D. However, when testing it seems another model is required. L57 of test_one_image.py is latend_id = model.netArc(img_id_downsample), but model.netArc is loaded from arcface_checkpoint.tar you share. I cannot find any definition about the model architecture of that. So is it defined in this repo? If not, will you release the architecture? Thanks!

ExponentialML commented 2 years ago

This is an interesting question that I'm interested in. While I'm not the author, I believe this checkpoint was trained on a similar network related to pix2pixHD (or some other image to image translation). The part of the code you are referring to is heavily referenced from here, which is probably how this network was trained.