tudor-berariu / fisher-information-matrix Goto Github PK
View Code? Open in Web Editor NEWPyTorch implementation of FIM and empirical FIM
PyTorch implementation of FIM and empirical FIM
can we compute fisher information for regression data? how to calculate it with pytorch?
Hi Tudor,
I feel grateful that you release the codes and they are helpful. However, I have a question here.
L48 - L52 in fim.py:
logits = model(data)
if empirical:
outdx = target.unsqueeze(1)
else:
outdx = Categorical(logits=logits).sample().unsqueeze(1).detach()
Here the logits are the output of the model, whose last layer is log_softmax
. So the logits might be negative rather than rational probabilities, which makes outdx
meaningless. Am I understanding wrong somewhere? Or should we add a line logits = torch.exp(logits)
?
Thanks for your attention.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.