We present Theseus, an efficient application-agnostic open source library for differentiable nonlinear least squares (DNLS) optimization built on PyTorch, providing a common framework for end-to-end structured learning in robotics and vision. Existing DNLS implementations are application specific and do not always incorporate many ingredients important for efficiency. Theseus is application-agnostic, as we illustrate with several example applications that are built using the same underlying differentiable components, such as second-order optimizers, standard costs functions, and Lie groups. For efficiency, Theseus incorporates support for sparse solvers, automatic vectorization, batching, GPU acceleration, and gradient computation with implicit differentiation and direct loss minimization. We do extensive performance evaluation in a set of applications, demonstrating significant efficiency gains and better scalability when these features are incorporated. Project page: https://sites.google.com/view/theseus-ai
翻译:我们展示了Tesus, 这是一种高效的应用程序-不可允许开放源库,用于在PyTorrch的基础上实现不同非线性最小方(DNLS)优化,为机器人和愿景的端到端结构学习提供了一个共同框架。现有的DNLS实施是具体应用,并不总包含许多对效率很重要的要素。Tesus是应用程序-不可知性,正如我们用几个例子说明的那样,这些应用程序是使用相同的可区分基本组成部分,如二阶优化器、标准成本功能和 Lie Group等构建的。关于效率,Tesus包含对稀有的解决问题器、自动传导、批发、GPU加速和梯度计算的支持,并隐含了差异和尽量减少直接损失。我们在一系列应用中进行了广泛的绩效评估,表明在纳入这些特征时效率的显著提高和更好可扩展性。项目网页:https://sitems.gogle.com/view/theus-ai。