VIP内容

PyTorch非常容易学习,并提供了一些高级特性,比如支持多处理器,以及分布式和并行计算。PyTorch有一个预训练模型库,为图像分类提供开箱即用的解决方案。PyTorch提供了进入尖端深度学习的最易访问的切入点之一。它与Python编程语言紧密集成,因此对于Python程序员来说,编写它似乎是自然和直观的。独特的、动态的处理计算图的方法意味着PyTorch既高效又灵活。

本书是为那些想要使用PyTorch进行深度学习的人而写的。目的是通过直接实验让您了解深度学习模型。这本书非常适合那些熟悉Python,了解一些机器学习基础知识,并正在寻找一种方法来有效地发展他们的技能的人。这本书将集中在最重要的特征和给出实际的例子。它假设您有Python的工作知识,并熟悉相关的数学思想,包括线性代数和微分。这本书提供了足够的理论,让你开始和运行,不需要严格的数学理解。在本书结束时,您将有一个深度学习系统的实用知识,并能够应用PyTorch模型来解决您关心的问题。

成为VIP会员查看完整内容
0
64

最新论文

Model-based reinforcement learning is a compelling framework for data-efficient learning of agents that interact with the world. This family of algorithms has many subcomponents that need to be carefully selected and tuned. As a result the entry-bar for researchers to approach the field and to deploy it in real-world tasks can be daunting. In this paper, we present MBRL-Lib -- a machine learning library for model-based reinforcement learning in continuous state-action spaces based on PyTorch. MBRL-Lib is designed as a platform for both researchers, to easily develop, debug and compare new algorithms, and non-expert user, to lower the entry-bar of deploying state-of-the-art algorithms. MBRL-Lib is open-source at https://github.com/facebookresearch/mbrl-lib.

0
0
下载
预览
Top