Latte: Cross-framework Python Package for Evaluation of Latent-Based Generative Models
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 30 references that are in the map. First posted on arXiv 20 Dec 2021.
Builds on
18 of 30 references.
References · 18
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
- 2018Disentangling by Factorisingcited by 616
- 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
- 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 241
- 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
- 2019On the Fairness of Disentangled Representationscited by 144
- 2018Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustnesscited by 108
- 2018Learning Deep Disentangled Embeddings with the F-Statistic Losscited by 101
- 2019Are Disentangled Representations Helpful for Abstract Visual Reasoning?cited by 100
- 2019Weakly Supervised Disentanglement with Guaranteescited by 82
6 more
- 2019Disentangling Factors of Variation Using Few Labelscited by 57
- 2019Unsupervised Model Selection for Variational Disentangled Representation Learningcited by 46
- 2020Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modellingcited by 45
- 2021Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectivescited by 7
- 2021Is Disentanglement enough? On Latent Representations for Controllable Music Generationcited by 7
- 2021Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributescited by 1
Built on by
Not cited yet.