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...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/164060 |
| _version_ | 1811677646569865216 |
|---|---|
| author | Watcharasupat, Karn N. Lee, Junyoung Lerch, Alexander |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Watcharasupat, Karn N. Lee, Junyoung Lerch, Alexander |
| author_sort | Watcharasupat, Karn N. |
| collection | NTU |
| description | 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. |
| first_indexed | 2024-10-01T02:40:41Z |
| format | Journal Article |
| id | ntu-10356/164060 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:40:41Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1640602023-01-04T01:01:46Z Latte: cross-framework Python package for evaluation of latent-based generative models Watcharasupat, Karn N. Lee, Junyoung Lerch, Alexander School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Engineering::Computer science and engineering Deep Generative Networks Disentanglement Learning 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. Published version 2023-01-04T01:01:46Z 2023-01-04T01:01:46Z 2022 Journal Article Watcharasupat, K. N., Lee, J. & Lerch, A. (2022). Latte: cross-framework Python package for evaluation of latent-based generative models. Software Impacts, 11, 100222-. https://dx.doi.org/10.1016/j.simpa.2022.100222 2665-9638 https://hdl.handle.net/10356/164060 10.1016/j.simpa.2022.100222 2-s2.0-85123614570 11 100222 en Software Impacts © 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). application/pdf |
| spellingShingle | Engineering::Electrical and electronic engineering Engineering::Computer science and engineering Deep Generative Networks Disentanglement Learning Watcharasupat, Karn N. Lee, Junyoung Lerch, Alexander Latte: cross-framework Python package for evaluation of latent-based generative models |
| title | Latte: cross-framework Python package for evaluation of latent-based generative models |
| title_full | Latte: cross-framework Python package for evaluation of latent-based generative models |
| title_fullStr | Latte: cross-framework Python package for evaluation of latent-based generative models |
| title_full_unstemmed | Latte: cross-framework Python package for evaluation of latent-based generative models |
| title_short | Latte: cross-framework Python package for evaluation of latent-based generative models |
| title_sort | latte cross framework python package for evaluation of latent based generative models |
| topic | Engineering::Electrical and electronic engineering Engineering::Computer science and engineering Deep Generative Networks Disentanglement Learning |
| url | https://hdl.handle.net/10356/164060 |
| work_keys_str_mv | AT watcharasupatkarnn lattecrossframeworkpythonpackageforevaluationoflatentbasedgenerativemodels AT leejunyoung lattecrossframeworkpythonpackageforevaluationoflatentbasedgenerativemodels AT lerchalexander lattecrossframeworkpythonpackageforevaluationoflatentbasedgenerativemodels |