cooper-org/cooper
A general-purpose, deep learning-first library for constrained optimization in PyTorch
This helps deep learning practitioners train machine learning models that need to satisfy specific rules or limits, even when these constraints are complex or non-convex. You provide your model, data, and the constraints it needs to follow, and the library helps adjust the model's parameters so it performs well while respecting those boundaries. This is for machine learning engineers, researchers, and data scientists working with advanced deep learning models.
153 stars.
Use this if you need to train deep learning models where the performance or output must adhere to complex, real-world constraints that can't be easily projected or simplified.
Not ideal if your optimization problems do not involve deep learning, or if your constraints are simple and can be handled by basic projection-based methods.
Stars
153
Forks
14
Language
Python
License
MIT
Category
Last pushed
Nov 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cooper-org/cooper"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.