Avoid reducing the model but continue the pipeline.

datitran / face2face-demo

pix2pix demo that learns from facial landmarks and translates this into a face

https://medium.com/@datitran/face2face-a-pix2pix-demo-that-mimics-the-facial-expression-of-the-german-chancellor-b6771d65bf66

MIT License

1.44k stars 423 forks source link

Avoid reducing the model but continue the pipeline. #40

Closed ysig closed 4 years ago

ysig commented 4 years ago

Hi,

I am using your nice repo for a video instead of a webcam. As so, I don't want to sacrifice quality for speed. Is there a way to keep the generative part of the pix to pix model without reducing it? I see a huge difference in my validation set rather than my generation using a reduce model and I don't want that. Is it easy to bypass this inside the code of reduce_model.py while keeping the rest of the pipeline intact?

Thanks in advance

ysig commented 4 years ago

After investigating the code, the model is not reduced in dimensionality.