Pixyz: a Python library for developing deep generative models

With the recent rapid progress in the study of deep generative models (DGMs), there is a need for a framework that can implement them in a simple and generic way. In this research, we focus on two features of DGMs: (1) deep neural networks are encapsulated by probability distributions, and (2) model...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Advanced robotics Ročník 37; číslo 19; s. 1221 - 1236
Hlavní autoři: Suzuki, Masahiro, Kaneko, Takaaki, Matsuo, Yutaka
Médium: Journal Article
Jazyk:angličtina
Vydáno: Taylor & Francis 02.10.2023
Témata:
ISSN:0169-1864, 1568-5535
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:With the recent rapid progress in the study of deep generative models (DGMs), there is a need for a framework that can implement them in a simple and generic way. In this research, we focus on two features of DGMs: (1) deep neural networks are encapsulated by probability distributions, and (2) models are designed and learned based on an objective function. Taking these features into account, we propose a new Python library to implement DGMs called Pixyz. This library adopts a step-by-step implementation method with three APIs, which allows us to implement various DGMs more concisely and intuitively. In addition, the library introduces memoization to reduce the cost of duplicate computations in DGMs to speed up the computation. We demonstrate experimentally that this library is faster than existing probabilistic programming languages in training DGMs.
ISSN:0169-1864
1568-5535
DOI:10.1080/01691864.2023.2244568