pytorch_gum_uncertainty_propagation
v0.18.0
Getting started:
GUM-compliant_neural-network_uncertainty-propagation
Getting started
Documentation
Disclaimer
License
Detailed information:
Installation
Quick setup (
not recommended
)
Updating to the newest version
Proper Python setup with virtual environment (
recommended
)
Set up a virtual environment
Create a
venv
Python environment on Windows
Create a
venv
Python environment on Mac & Linux
Install pytorch_gum_uncertainty_propagation via
pip
Optional Jupyter Notebook dependencies
Install known to work dependencies’ versions
Optional dependencies
Changelog
v0.18.0 (2023-01-24)
Feature
Documentation
v0.17.1 (2023-01-21)
Fix
Documentation
v0.17.0 (2023-01-20)
Feature
v0.16.0 (2023-01-20)
Feature
Documentation
v0.15.0 (2023-01-17)
Feature
Documentation
v0.14.0 (2022-12-21)
Feature
Documentation
v0.13.0 (2022-12-21)
Feature
Documentation
v0.12.0 (2022-12-21)
Feature
Fix
Documentation
v0.11.0 (2022-12-21)
Feature
Fix
v0.10.0 (2022-12-20)
Feature
Fix
Documentation
Performance
v0.9.0 (2022-12-17)
Feature
v0.8.0 (2022-12-17)
Feature
Documentation
v0.7.0 (2022-12-15)
Feature
Documentation
v0.6.0 (2022-12-14)
Feature
Fix
v0.5.0 (2022-12-11)
Feature
v0.4.0 (2022-12-11)
Feature
Documentation
v0.3.0 (2022-12-10)
Feature
Documentation
v0.2.0 (2022-12-09)
Feature
Documentation
v0.1.0 (2022-12-03)
Feature
Examples:
Examples
Proof-of-Concept examples
Script to propagate inputs for several architectures and activations
Utility module to construct valid covariance matrices from standard uncertainties
Visualizations of activation functions
Plot with Plotly
Graph of QuadLU
Graph of softplus
Graph of sigmoid
Propagate ZeMA samples through MLPs
ZeMA dataset API
Code Reference:
Modules
Functionals
Uncertainties
pytorch_gum_uncertainty_propagation
Propagate ZeMA samples through MLPs
Edit on GitHub
Propagate ZeMA samples through MLPs