Latte: cross-framework Python package for evaluation of latent-based generative models

Latte (for LATent Tensor Evaluation) is a Python library for evaluation of latent-based generative models in the fields of disentanglement learning and controllable generation. Latte is compatible with both PyTorch and TensorFlow/Keras, and provides both functional and modular APIs that can be easil...

Description complète

Détails bibliographiques
Auteurs principaux: Watcharasupat, Karn N., Lee, Junyoung, Lerch, Alexander
Autres auteurs: School of Electrical and Electronic Engineering
Format: Journal Article
Langue:English
Publié: 2023
Sujets:
Accès en ligne:https://hdl.handle.net/10356/164060
Description
Résumé:Latte (for LATent Tensor Evaluation) is a Python library for evaluation of latent-based generative models in the fields of disentanglement learning and controllable generation. Latte is compatible with both PyTorch and TensorFlow/Keras, and provides both functional and modular APIs that can be easily extended to support other deep learning frameworks. Using NumPy-based and framework-agnostic implementation, Latte ensures reproducible, consistent, and deterministic metric calculations regardless of the deep learning framework of choice.