Comments (3)
It is to reduce the test-time numerical domain gap. The size difference between texture syn input and the structure syn input can be seen as kind of a pre-padding. And we want such region to be at the saturated region (0.995 to 1 after tanh) of tanh, and so that when we extrapolate vertical coordinates at testing, the coordinates wont be too far away from it's training distribution (~1).
from infinitygan.
This figure may explain a bit of the concept, the red line is the result of the dividing by ss_spatial_size, and the green line is using the ts_spatial_size. Each color has three lines representing three different sizes of the features. The horizontal axis is the raw coordinate value, and the vertical axis is the value after tanh projection.
from infinitygan.
OK, I got it. Thanks for the explanation.
from infinitygan.
Related Issues (17)
- When will the code be released? HOT 10
- How we can test outpainting with an png image
- benchmark HOT 1
- Problem with training Flickr small dataset HOT 1
- Using infinityGan as an ultra high resolution image generator?
- Fused generation
- Cyclic coordinate
- How long does it take to train HOT 2
- Where is Dada?
- can not download the dataset HOT 5
- Code and training issues HOT 11
- NameError: name 'config' is not defined on prepare_data.py HOT 3
- i want to convert lmdb to png, but there is sth wrong with ParseFromString ,Could u share me the code? HOT 1
- Problems with outpainting HOT 1
- Problem with outpainting HOT 2
- Google Drive bad experience when downloading the dataset
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 infinitygan.