Comments (1)
Hi, thanks for raising this comparison, I didn't expect that there would be these differences! Regarding the split and squeeze: in general, either way (official implementation or notebook) is fine in theory, although I would expect the version in the tutorial to generalize a bit better. Splitting over pixel positions (in the official code) instead of channels (in the tutorial) seems to me much harder to learn, since you force the network to identify which pixels will be mapped to the prior at the early stage already, while the neural networks are convolutional and thus translation invariant (up to padding borders). So in the end, the model might have to map everything to the prior distribution, which can limit the capacity. In comparison, if you split over channels, it is much easier for the model to simply dedicate some dimensions to be mapped to Gaussians, especially since we use a similar splitting strategy in the coupling layers. Nonetheless, I have not explicitly tested it and thought the tutorial version was the more natural way.
For the coupling layers, the difference in channelwise versus rowwise coupling is how the network perceives the input. In channelwise, we have an input of 4x14x14, while the rowwise coupling has 1x28x28. Thus, different network architectures are learned here. Another key difference is when you start combining these layers with more sophisticated NF tricks. For instance, often invertible 1x1 convolutions are used to intermix the channels between coupling layers. This has a different effect if you squeeze or not.
Hope that helps :)
from uvadlc_notebooks.
Related Issues (20)
- [Question] ResNet pre actiovation blocks HOT 2
- [Question] Evaluating the loss for Autoencoders HOT 3
- About the same amount of images in every class HOT 1
- A question about Tutorial 6 - Transformers HOT 2
- [Question] Use of MLP in Transformer Encoder/Decoder HOT 2
- test_anom_dataset raised RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly' HOT 1
- Can PositionalEncoding used with position information? HOT 1
- [Question] Tutorial 11, Variational dequantization HOT 3
- Introduction_to_PyTorch.ipynb: Mean Sigma Formula HOT 1
- Introduction_to_PyTorch.ipynb: Typo HOT 1
- [Question]Tutorial 3(Pytorch, JAX) Test accuracy for the model with sigmoid activation function HOT 2
- Activation_Functions.ipynb : Learning rate Notation
- "Getting runtime error" HOT 2
- New tutorial request to extend Normalizing Flow HOT 1
- unable to use tensorboard in "Tutorial 16: Meta-Learning - Learning to Learn"
- [JAX] Meta Learning Tutorial? HOT 1
- A Formula Typo
- Tutorial 16 Meta Learning(Pytorch)
- [Question]Tutorial 5 (JAX) Max-pool branch for inception HOT 2
- Copyright on a gif 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 uvadlc_notebooks.