search

rotemtzaban / STIT

MIT License
1.2k stars 170 forks source link

Training my own InterfaceGAN boundary #18

Closed mazzzystar closed 2 years ago

mazzzystar commented 2 years ago

Thanks for your great work, the results were impressive!

I'd to train my own InterfaceGAN w_direction, and noticed that your w_direction vector(such as 'age.npy') is the size of (18, 512) rather than (1,512).

My previous experience was sampling a lot of images with their w counter part with the size of (1,512), then train a model for binary classification. So I wonder whether you're using w+ with the size of(18,512) for training InterfaceGAN?

Refer to https://github.com/omertov/encoder4editing/issues/9#issuecomment-806139382

mazzzystar commented 2 years ago 
>>> import numpy as np
>>> w = np.load('age.npy')
>>> w[0] == w[1]
array([ True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        True,  True,  True,  True,  True,  True,  True,  True,  True,
        ...
        True,  True,  True,  True,  True,  True,  True,  True])

Finally I realized each row for a (18, 512) of w are the same. Thanks a lot.