Comments (6)
Hi,
This is just a convention. You may simply flip the figure and call the training direction "inverse" and the sampling direction "forward" and nothing would change, that is, the internal operation in the layers would not change. Hope this helps!
from noise_flow.
The training process is to sample the noise distribution (the latent space like z in Glow) to the noisy image (the data space like x in Glow). The goal of this work is to get the noise distribution at last (which is the inference in Glow). Therefore, the inverse direction is used as training here which is different from Glow which use the data space to approximate latent space as training.
I think my understanding may be the same as you and if there is anything wrong, please let me know !
from noise_flow.
What's more, is there the pytorch implementation of Noise Flow?
from noise_flow.
Just to clarify, in the noise flow paper, Figure 3, and in the code:
- The training is in the inverse direction: noise distribution --> normal distribution.
- The sampling is in the forward direction: normal distribution --> noise distribution.
- There might be a confusion from the fact that the noise distribution is denoted as
n
in the paper; but denoted asx
in the code. Also, the normal distribution is denoted asx_0
in the paper; but denoted asz
in the code.
So, at the end, I don't see a difference in the training/sampling directions compared to the Glow model.
from noise_flow.
What's more, is there the pytorch implementation of Noise Flow?
Not currently; I hope we can do it in the future.
from noise_flow.
In the Glow, data space distribution --> normal distribution which is the training in your comment uses the forward calculation however use the inverse calculation in Noise Flow code (such as _inverse_and_log_det_jacobian function of all layers).
I think it is the difference and ask why use the inverse calculation instead of forward.
from noise_flow.
Related Issues (9)
- Question about dequantization HOT 2
- FTP server is not available HOT 1
- FileNotFoundError HOT 2
- Sample noise flow add to SIDD raw image problem using the pre-train model provided HOT 12
- Sample noise directly on sRGB images
- how to reproduce you model used in the papar by training from scratch? HOT 4
- How to adapt your code into another dataset HOT 2
- TimeoutError: [Errno 110] Connection timed out HOT 2
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 noise_flow.