Pixyz: a library for developing deep generative models

28 Jul 2021  ·  Masahiro Suzuki, Takaaki Kaneko, Yutaka Matsuo ·

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 DGM library called Pixyz. This library adopts a step-by-step implementation method with three APIs, which allows us to implement various DGMs more concisely. 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.

PDF Abstract
No code implementations yet. Submit your code now

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here