Open WJ-Lai opened 4 years ago
What do you mean by boundary?
For smile direction it makes sense to only alter the coarse layers and leave the fine layers alone. I would've thought other directions such as gender and age would need to change all the layers though. ¯\(ツ)/¯
@WJ-Lai The smile direction was found in W space, but the Puzer's encoded latent from W+ space.
Hi, thanks for sharing this great work!
I have some question as follow:
The shape of 'donald_trump_01.npy' is (18,512) which has different values of 18 layers. However, your "smile.npy" has the same values of 18 layers. The meaning of 18 layers of 'donald_trump_01.npy' is different because the values are different, why it can edit by the same smile boundary? Do you know why it can also work?
In move_and_show function,
new_latent_vector[:8] = (latent_vector + coeff*direction)[:8]
. Why just edited the first eight layers?Thank you!