GenSBI#

Tests Coverage

GenSBI Logo

Work in progress!#

GenSBI is a work in progress, and we are actively developing new features and improvements. Expect the API and examples to evolve over time. We welcome contributions and feedback from the community!

Getting Started#

To get started with GenSBI, install the package using pip:

pip install git+https://github.com/aurelio-amerio/GenSBI.git[cuda12]

We advise to take a look at the Getting Started page for additional installation instructions and basic usage.

You can also explore the Examples page for practical demonstrations of GenSBI’s capabilities.

You can find the API documentation in the API Documentation section.

Examples#

two-moons posterior sampling two-moons posterior sampling

Examples for this library are available separately in the GenSBI-examples repository.

Some key examples include:

Unconditional Density Estimation:

  • flow_matching_2d_unconditional.ipynb Open In Colab
    Demonstrates how to use flow matching in 2D for unconditional density estimation.

  • diffusion_2d_unconditional.ipynb Open In Colab
    Demonstrates how to use diffusion models in 2D for unconditional density estimation.

Conditional Density Estimation:

  • two_moons_flow_simformer.ipynb Open In Colab
    Uses the Simformer model for posterior density estimation on the two-moons benchmark.

  • two_moons_flow_flux.ipynb Open In Colab
    Uses the Flux1 model for posterior density estimation on the two-moons benchmark.

  • gaussian_linear_flow_flux1joint.ipynb Open In Colab
    Uses the Flux1Joint model for posterior density estimation on the Gaussian Linear benchmark.

  • slcp_flow_simformer.ipynb Open In Colab
    Uses the Simformer model for posterior density estimation on the SLCP benchmark.

Table of Contents#