Comments (1)
Yes, and thank you for bringing this up.
In MC Dropout we apply dropout every time we make a .forward() call, and we compute a MC estimate of the loss using one MC sample (i.e. one forward pass). You are right that the equivalent of BBB for MC Dropout should contain a variable number of samples, and the MC loss should be the average of the sampled losses. Instead, we implicitly (and probably not very transparently) assume no_samples=1 for MC Dropout.
For reference, we did not observe a significant dependence on the quality of our solutions by increasing the number of samples up to ~10 samples. We will modify MC Dropout to be more general, as soon as we get the time.
from bayesian-neural-networks.
Related Issues (20)
- bbp_hetero uncertainties plot HOT 2
- Energy Efficient dataset HOT 1
- Posterior Predictive Distribution HOT 5
- [Question] BBB vs BBB w/ Local Reparameterization HOT 4
- About calculating the logarithm of the Gaussian mixture model HOT 1
- UCI log likelihood calculation HOT 5
- Scaling langevin noise HOT 2
- Looking for the implementation of "Getting a GlUE" HOT 1
- Thank you!
- [Question][MC dropout] drop hidden units for each data point or for each mini-batch data? HOT 1
- code implementation HOT 1
- May I ask the code about calculating the Hessian in the Kronecker-Factorised Laplace methods? HOT 1
- Question: log_gaussian_loss function used in MC Dropout and SGLD HOT 1
- this code is writen in python 2.7 .can this code change to the envriment of python 3.6 HOT 1
- 2 questions: batch & layer HOT 1
- a question about the calculation of uncertainty HOT 1
- bbp_hetero notebook is not using three layers HOT 1
- Panda not reading the first row HOT 1
- BNN Bayesian Online Learning 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 bayesian-neural-networks.