Comments (2)
I believe the initializations made it faster to train. logits
are mixture parameters and initialized to be uniform. means
are initialized to be uniformly distributed across the entire range of possible values (e.g. evenly spaced bins from 0-255 if we're doing rgb values). log_scales
are just initialized randomly, but could also be initialized to unit variance. Overall, I think the means
initialization helped the most and the logits
and log_scales
initializations could be zeros or randn.
from deepul.
Thank you very much !
from deepul.
Related Issues (12)
- Bug in MADE sampling implementation in 'hw1_solutions.ipynb' HOT 1
- `optimizer.zero_grad` called after calculating loss instead of before in `lecture3_flow_models_demos.ipynb`.
- HW2 autoregressive flow for images solution issue HOT 3
- Is log_det in preprocess function useful? HW2 HOT 1
- Where is HW 4? HOT 1
- Question regarding solutions availability
- HW1 MADE | possible flaws in solution implementaiotn. HOT 2
- Flows demo fails because of missing `.to(ptu.device)` HOT 2
- ActNorm implementation missing division by `std` on the shift parameter
- Reporting bugs/errors in `lecture3_flow_models_demos.ipynb` HOT 4
- What is `self.loc` in `MixtureCDFFlow` class? HOT 1
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 deepul.