Comments (7)
You can set k=1
for all directions for a fair comparison.
from sefa.
hi,In this table, you mentioned " each level of layers", for example, Middle Layers (2-5), means 2-5 layers together as a whole matrix or a matrix for each layer? I think it must satisfy linearity, but 2-5 layers together is not linearity because there is nonlinear activation function between them.
from sefa.
If you only consider how the latent code is fed into these AdaIN operations for each layer, they are linear.
from sefa.
Suppose layer2's weight matrix size is [1024,512], layer3's size is [512,512], layer 4's size is [256,512]. If consider layer2~4, it firstly concatenate them together and get a [1024+512+256,512]=[1792,512] size matrix A, and compute A^T A's eigen vector as the direction?
from sefa.
@07hyx06 Yes, you are right.
from sefa.
@07hyx06 Yes, you are right.
I concatenate all of the 18 layers together and get a [10176,512] weight matrix A, and then normalized A's row by A[i]/=torch,norm(A[i]) before performing eigen decomposition, but i still cannot get the results in Table 1. The cos distance in my implement is 0.8+ for all attribute. Is it needs other tricks? I used torch.symeig to compute the eigens and the biggest eigen is 60 6.55.
from sefa.
Please try np.linalg.eig(A.T.dot(A))
from sefa.
Related Issues (20)
- reproduce results matched figure 5 in paper HOT 1
- A question about the assumption of the method HOT 1
- About attribute predictor and re-scoring analysis. HOT 5
- Compability issue for .pkl extension HOT 2
- StyleGAN2 LSUN bedroom HOT 1
- Direction indices for Closed Form applied on PGGAN HOT 1
- Edit face in Eyeglasses, Gender, Hair Color, Pose , Smile ... direction failed HOT 1
- I can't run this scripts
- StyleGAN3 Support HOT 1
- Annotations corresponding to eigen vectors
- StyleGAN 2 ADA transfer learning sourcenet error HOT 1
- Help -- factorize_weight --
- streetscapes stylegan 2 model
- Using a custom model HOT 22
- EOFError: Ran out of input HOT 1
- Some questions about your code HOT 3
- BigGAN HOT 4
- Question about factorize_weight() HOT 1
- About ignore the non-linear layers of the mapping net. HOT 4
- how to directly use checkpoint from stylegan2-ada-pytorch HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sefa.