自2017年推出以来，transformers已迅速成为在各种自然语言处理任务中实现最佳结果的主导架构。如果你是一名数据科学家或程序员，这本实践用书将向你展示如何使用Hugging Face Transformers(基于Python的深度学习库)训练和扩展这些大型模型。 Transformers已经被用来撰写真实的新闻故事、改进Google搜索查询，甚至创建会讲老套笑话的聊天机器人。在这本指南中，作者Lewis Tunstall、Leandro von Werra、Thomas Wolf(Hugging Face Transformers的创建者)通过实践方法来教你如何使用transformers以及如何将它集成到你的应用中。你将快速学习可以由transformers帮助解决的各种任务。 为核心NLP任务构建、调试和优化transformers模型...(展开全部)

This witty and fascinating study reminds us that there was animation before Disney: about thirty years of creativity and experimentation flourishing in such extraordinary work as Girdie the Dinosaur and Felix the Cat. Before Mickey, the first and only in-depth history of animation from 1898-1928, includes accounts of mechanical ingenuity, marketing and art. Crafton is equally a...(展开全部)

Learn how to use generative media techniques with AI to create novel images or music in this practical, hands-on guide. Data scientists and software engineers will understand how state-of-the-art generative models work, how to fine-tune and adapt them to your needs, and how to combine existing building blocks to create new models and creative applications in different domains. ...(展开全部)

Since their introduction in 2017, Transformers have quickly become the dominant architecture for achieving state-of-the-art results on a variety of natural language processing tasks. If you're a data scientist or machine learning engineer, this practical book shows you how to train and scale these large models using HuggingFace Transformers, a Python-based deep learning library...(展开全部)

The official guide to Dreamwave's all-new Transformers universe continues with new bios written just for this series, along with more fantastic art of classic characters. There are plenty of Transformers favorites, plus profiles of lesser-known stars, making this the complete resource for Generation One fans, who can catch up with their favorite main characters as they uncover ...(展开全部)

Explore the fascinating world of anime through 30 classic films in this new book from the authors of Ghibliotheque The Ghibliotheque Guide to Anime gives an accessible beginner's tour to the wildly popular world of Japanese animated cinema, charting a path that takes in everything from titans of the industry like Akira, Ghost in the Shell and Your Name, to deeper cuts, hidden g...(展开全部)

日本动画80年—— 宫崎骏、大友克洋、川尻善昭、押井守、今 敏、汤浅政明、庵野秀明、新海诚、细田守……30位导演、30部经典动画，一窥日本动画产业的轨迹 从类型、主题、视觉表现到各世代天才名导 破解日本动画席卷全球的织梦技术 带领读者进入日本动画的神奇世界 知名Podcast节目“吉卜力图书馆”（Ghibliotheque）主持人杰克汉和麦可，继广受好评的《吉卜力电影完全指南》之后再次出击。这次的野心更大，他们揭开80年来日本动画风靡世界的神秘面纱，带领读者探访日本动画产业的轨迹，分析这些动画的看点，并分享幕后制作的精彩故事。 本书从1958年的《白蛇传》开始，以2021年的《龙与雀斑公主》结束，作者以一位导演一部片为原则，选出30部最具代表性的动画。在漫长60多年的时光里，媒介技术、表现形式、动画制作的体制与劳动等问题不断演变。在其中，雄心壮志往往...(展开全部)

本书涵盖了Transformer在NLP领域的主要应用。首先介绍Transformer模型和Hugging Face 生态系统。然后重点介绍情感分析任务以及Trainer API、Transformer的架构，并讲述了在多语言中识别文本内实体的任务，以及Transformer模型生成文本的能力，还介绍了解码策略和度量指标。接着深入挖掘了文本摘要这个复杂的序列到序列的任务，并介绍了用于此任务的度量指标。之后聚焦于构建基于评论的问答系统，介绍如何基于Haystack进行信息检索，探讨在缺乏大量标注数据的情况下提高模型性能的方法。最后展示如何从头开始构建和训练用于自动填充Python源代码的模型，并总结Transformer面临的挑战以及将这个模型应用于其他领域的一些新研究。