relucent 0.1.0

No project description provided

Relucent

Explore polyhedral complexes associated with ReLU networks

Environment Setup

1. Install Python 3.13
2. Install PyTorch 2.3.0
3. Install the remaining dependencies with pip install -r requirements.txt

Code Structure

• model.py: PyTorch Module that acts as an interface between the model and the rest of the code
• poly.py: Class for calculations involving individual polyhedrons (e.g. computing boundaries, neighbors, volume)
• complex.py: Class for calculations involving the polyhedral cplx (e.g. polyhedron search, connectivity graph calculation)
• convert_model.py: Utilities for converting various PyTorch.nn layers to Linear layers
• bvs.py: Data structures for storing large numbers of sign vectors

Obtaining a Gurobi License

The following steps are not necessary when replicating the experiments from the paper.

Without a license, Gurobi will only work with a limited feature set. This includes a limit on the number of decision variables in the models it can solve, which limits the size of the networks this code is able to analyze. There are multiple ways to install the software, but we recommend the following steps to those eligible for an academic license:

1. Install the Gurobi Python library, for example using pip install gurobipy
2. Obtain a Gurobi license (Note: a WLS license will limit the number of concurrent sessions across multiple devices, which can result in slowdowns when using this library on different machines simultaneously.)
3. In your Conda environment, run grbgetkey followed by your license key