Comments (1)
Hi @Yuzhi-Yang,
We do a forward pass and we sample from the activations using local reparameterization trick and starting with a normal distribution. This is equivalent to learning the MAP of the variational posterior
probability distribution qθ(w|D). Then we do another conv forward pass and then we sample again. Now the variance in the sampled value with the previous MAP is noted and it acts as the variance between the outputs. We can do technically as many passes as we want and capture the weight to get a better variance but that would be very expensive. So, we limit it. Now the means can be averaged and the variance is what we learn and we keep these mean and variance going forward.
from pytorch-bayesiancnn.
Related Issues (20)
- Ouput Variance
- Old version of KL Divergence HOT 1
- Can I drop the KL term in loss function. HOT 1
- CPU/GPU Spec you've used for running main_bayesian.py HOT 2
- MNIST training data from yann lecun is not available (503 Service Unavailable)
- What is the function of the fixed prior value (i.e., prior_mu and prior_sigma) ?
- Why is model put in train mode in validation? HOT 2
- use bayes for segementation HOT 1
- Input argument for ELBO criterion HOT 3
- Missing sum in Epistemic and Aleatoric computation
- Sample always = True in forward method of the BBBConv2D class?
- Cant get uncertainty estimation for custom dataset
- GPU Memory usage
- forward and outputs of models HOT 1
- Is there a tensorflow version BayesianCNN?
- Question about calculate_kl
- net.train() in validation and test phase.
- num_ens
- dataset HOT 2
- running error
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 pytorch-bayesiancnn.