Comments (4)
As far as I am concerned, the GLOW (or normalization flow) model try to max likelihood of training data, which means max the log probability (the var objective
in my code) and thus means min the -objective
.
logdet += float(-np.log(256.) * pixels)
About this line, I cannot recall the details. It is supposed to handle some extra multiplication factor out of det()
.
-np.log(256.)
is used to approx intergration for discrete pixel values.pixels
handles the (width, height) dimension of input.
from glow-pytorch.
Well, from my reading in another paper "Generative Flow via n * n Convolution: Thanh-Dat Truong et al.".
The data is added with a random uniform noise, which is the discretization level of the data, making the input continuous.
Could you get some hint? (I'm still confused...)
from glow-pytorch.
float(-np.log(256.) * pixels)
discretized level is a number denote the range of 8 bit pixel (2^8=256). So, glow paper mentioned c=-M x log a
, where a=256
in Eq(2), while M is the number of total pixels in your image (i.e. 32 * 32 image, M=32*32
).
from glow-pytorch.
@chaiyujin i wonder why the objectives will need to divided by float(np.log(2.) * pixels
? what is that means ?
from glow-pytorch.
Related Issues (20)
- Dataset Issue HOT 4
- License HOT 1
- Question about LinearZeros and Conv2dZeros HOT 4
- Positive logdet HOT 5
- Sampling Fails when moving to CIFAR10 HOT 3
- Broken paralelization HOT 4
- about "cross" split
- NLL numbers on popular datasets HOT 1
- [encoder part problem] generate_z() HOT 3
- Reconstructed images are not like the input images HOT 2
- Separate prior for each element of the batch.
- Infinite values in generated images HOT 7
- Hard to understand mean and logs in Split2d Module HOT 2
- Multiscale Architecture HOT 3
- How to generate larger images? HOT 1
- Inquiry about actnorm layer implementation HOT 1
- How to adapt this code to torchvion.dataset? HOT 1
- to onnx?
- Invertibility of Glow HOT 5
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 glow-pytorch.