bayesian-inverse-graphics
Bayesian Inverse Graphics for Few-Shot Concept Learning
MIT License
Stars
6
Ecosystems:
Python
Bayesian Inverse Graphics (BIG)
This repository contains the code for the paper "Bayesian Inverse Graphics for Few-Shot Concept Learning"
TLDR: probabilistic programming + differentiable rendering = minimal-data learning
Modules
All modules are implemented in jax
- jaynes Probabilistic Programming Library (Automatic Bayesian Inference).
- tamayo Differentiable Rendering Library.
- lecun Convnets.
Run
Setup
- Install requirements e.g.
pip install -r requirements.txt - Download the datasets (fscvlr.zip) and weights (VGG16.eqx) from here.
- Move
fsclvr.zipinside repositorybayesian-inverse-graphics/. - Move
VGG16.eqxinside repositorybayesian-inverse-graphics/. - Extract datasets
unzip fsclvr.zip
Training
- Run
python optimize_scene.py - Run
python extract_features.py - Run
python optimize_bijectors.py
Test
- Run
python learn_concept.py --concept 0
Funding
This project was developed in the Robotics Group of the University of Bremen, together with the Robotics Innovation Center of the German Research Center for Artificial Intelligence (DFKI) in Bremen. It has been funded by the German Federal Ministry for Economic Affairs and Energy and the German Aerospace Center (DLR), in the PhysWM project.