Comments (1)
y-prudent
commented on July 30, 2024
- In the tutorial section of the doc: MLP / MSP lead to the Getting started tutorial, it would be more logical to return a link for separate torch and tf MLP / MSP notebooks.
- In readme and index.md, add a note about
prepare-dev-torchandprepare-dev-tffor users that want an installation for a specific backend. - In index.md, the title "For benchmarking with one dataset as in-distribution and another as out distribution" appears 2 times
- Fix broken links in the doc, and remove the link leading to the main doc page from the main doc page (cf. You can find the doc here => useless)
- Fix inconsistent preprocessing fn between torch and tf (#56)
- Do better plots with info about AUROC etc. (#57)
from oodeel.
Related Issues (20)
- Improve feature extractor for intermediate outputs
- Add temperature to energy
- General remarks on docs
- Add score_predict to avoid duplicate forwards when also using the model for inference
- Enforce user to fit dataset when needed in a baseline
- performances issues in tf
- Add option to return features + labels in feature extractors
- OODDataset name is confusing HOT 1
- Update plots in docs/pages notebooks
- output_layer_id should be required in the fit instead of instanciation of ood detector
- Feature concatenation
- React automatically applies to the -2th layer of the model
- Logits as attribute of the FeatureExtractor?
- Add MSP class as a partial of MLS with output_activation set to "softmax"?
- Hide private methods in API reference (MkDocs) HOT 1
- Change default value of nearest in DKNN to 50
- New plots
- Reformat doc section relative to OOD methods
- On taking the maximum projection on SHE patterns
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 oodeel.