Skip to content

Latest commit

 

History

History
27 lines (17 loc) · 665 Bytes

README.md

File metadata and controls

27 lines (17 loc) · 665 Bytes

This repository contains associated code for the ICLR 2023 paper Differentiable Mathematical Programming for Object-Centric Representation Learning.

Requirements

Usage

Pretrained model checkpoint can be loaded using the Jupyter notebook for evaluation.

PYTHONPATH=. python slot_cut/train.py

Set hyperparameters in slot_cut/params.py

Acknowledgements

The repository uses code from https://github.com/untitled-ai/slot_attention and resnet code from https://github.com/kuangliu/pytorch-cifar