GitHub / msmrexe / pytorch-energy-based-generative-models
A PyTorch implementation of Energy-Based Models (EBMs) leveraging Langevin dynamics for generative modeling on the MNIST dataset. This project explores learning a joint distribution of data and labels by minimizing an energy function, allowing for both discriminative classification and synthetic image generation.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msmrexe%2Fpytorch-energy-based-generative-models
PURL: pkg:github/msmrexe/pytorch-energy-based-generative-models
Stars: 1
Forks: 0
Open issues: 0
License: mit
Language: Python
Size: 35.2 KB
Dependencies parsed at: Pending
Created at: about 1 month ago
Updated at: about 1 month ago
Pushed at: about 1 month ago
Last synced at: about 1 month ago
Topics: course-project, energy-based-model, generative-models, hybrid-loss, image-generation, langevin-dynamics, logsumexp, mnist-dataset, pytorch, university-project