Page 1 of 1
training sets and inputs
Posted: Sun Feb 16, 2020 11:55 am
by siliconunit
Hi!,
Great project! getting decent results,(1080 8gb / ryzen 7), and my face B is homemade HD filming.
I 've got a couple of questions thought!:
- Can I increase the number of A or B faces on the fly? ie stop the training, update the folders, that's it ? (I'm using Villain)
2.Once I train face A and face B , is there a way to recycle the face B training part ?
SU
Re: training sets and inputs
Posted: Sun Feb 16, 2020 11:57 am
by torzdf
Hello and welcome!
Your first question is answered here:
app.php/faqpage#f3r4
As to the second, it is possible to just replace the "A" data, to recycle "B", but this usually results in identity leak, so it's best to start a new model with your required pair.
Re: training sets and inputs
Posted: Sun Feb 16, 2020 12:30 pm
by siliconunit
Awesome! I missed that bit !:)
What about gray-scale images, are they a good thing or will get confusing?
Thanks!
Re: training sets and inputs
Posted: Sun Feb 16, 2020 4:56 pm
by torzdf
Should be ok in moderation.
Re: training sets and inputs
Posted: Sun Feb 16, 2020 9:58 pm
by djandg
FYI - I've tried all greyscale images as one of the faces for training, result was poor (color wise and sharpness wise) swapping on a color video at 250k iters, original model. B&W images were also of poor quality due to being extracted from a film from the 1930's.
Re: training sets and inputs
Posted: Mon Feb 17, 2020 6:47 am
by bryanlyon
All greyscale/poor quality on one side is not-ideal and will almost always lead to failure. This is due to the inability for the model to learn sufficient information from the poor quality source data.