圖書標籤: 深度學習 Python 機器學習 人工智能 Keras DeepLearning 計算機 編程
发表于2025-01-23
Deep Learning with Python pdf epub mobi txt 電子書 下載 2025
Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library. Written by Keras creator and Google AI researcher François Chollet, this book builds your understanding through intuitive explanations and practical examples. You'll explore challenging concepts and practice with applications in computer vision, natural-language processing, and generative models. By the time you finish, you'll have the knowledge and hands-on skills to apply deep learning in your own projects.
François Chollet works on deep learning at Google in Mountain View, CA. He is the creator of the Keras deep-learning library, as well as a contributor to the TensorFlow machine-learning framework. He also does deep-learning research, with a focus on computer vision and the application of machine learning to formal reasoning. His papers have been published at major conferences in the field, including the Conference on Computer Vision and Pattern Recognition (CVPR), the Conference and Workshop on Neural Information Processing Systems (NIPS), the International Conference on Learning Representations (ICLR), and others.
之前讀過本書作者的 blog 文章 User experience design for APIs,明白他能把很復雜的問題簡明扼要地講清楚,這本書也不例外,把很多道理講透瞭。適閤初學者入門,也適閤入門者迴顧基礎知識。
評分keras 的接口好像還挺穩定的。
評分應該改名deep learning in keras. 不過最後一段對於deep learning的看法和預想倒是很有前瞻性,值得閱讀。
評分語言平實,舉例精妙,第 9 章的展望是真知灼見。但同時挑幾個毛病:1) convolution 講得不算太清楚;2) LSTM 和 GRU 則是直接放棄瞭詳細敘述…… 3) Depthwise Separable Convolution 講得不算太清楚,請配閤閱讀 https://eli.thegreenplace.net/2018/depthwise-separable-convolutions-for-machine-learning;4) Deep Dream 沒看懂,不如看這個 https://www.youtube.com/watch?v=BsSmBPmPeYQ
評分1-4, 平庸,適閤復習,不適閤初學;5,transfer learning, visualization講的很好,惜無semantic segmentation等高級話題;7,keras技巧,對於組建DAG型網有用,我的感受是這些技巧對閱讀學術論文也有幫助
目前最通俗易懂的深度学习入门书,由Keras之父执笔。大神不但技术了得,文笔也不一般,真的就是为了让尽可能多的人能够使用深度学习而写的这本书,涵盖了深度学习的基础知识、Keras使用模式以及深度学习最佳实践。 学习本书需要具备基础的Python知识,但不需要深度学习或者机器...
評分 評分对于新手小白我来说是很好的入门介绍,从模型到应用都能略窥一二,顺带这个风格迁移真的很好玩儿,把我身处的城市画成梵高的世界,希望以后能从模仿到创新实现突破吧。 在看这本书期间我正好在做学校的大作业,有很多实用的评价模型,调参的部分都用在了大作业中,学以致用,越...
評分电子版8.4节,从300页开始出现了一个明显的错误,包括代码在内。 原文及代码中 decoder 使用 z = z_mean + exp(z_log_variance) * epsilon 生成 latent space 中的一个点,再依靠这些点的分布生成图像,这实际是对原图像分布的还原过程。 高斯分布可以使用 N~(μ, σ) 来描述,...
Deep Learning with Python pdf epub mobi txt 電子書 下載 2025