动手学深度学习

Hacker News 上怎么说

• nafizh · 2021 年

  如果你只想找一本书从头开始学习深度学习的所有内容，包括编码和最新技术，那应该是《动手学深度学习》（Dive into Deep Learning）[0]。被严重低估，且不太为人所知。 [0] https://d2l.ai/

  If you want just one book to learn all things deep learning from scratch with coding including the latest techniques, it should be Dive into deep learning [0]. Really underrated and not well-known. [0] https://d2l.ai/

• domenicrosati · 2022 年

  酷！是什么促使你写它的？我也觉得 d2l 的实现又好又简单 https://d2l.ai/chapter_attention-mechanisms/transformer.html pytorch 自带的那个也不错。 如果能在你的仓库里看到一些解码的例子就好了（如果我没看到请原谅）。我记得当我第一次从头实现一个 transformer 时，使用贪婪或束搜索生成序列之后……

  Cool! What motivated you to write it? I find the d2l implementation nice and simple as well https://d2l.ai/chapter_attention-mechanisms/transformer.html The one in pytorch itself isnt so bad either. Be nice to see some examples of decoding in your repo (forgive me if I dont see it). I remeber when i first implemented a transformer from scratch generating sequences using greedy or beam search aft

• credit_guy · 2019 年

  ……合并一些节点并拆分另一些节点，也许在 PyTorch 里很容易搞定。如果是这样的话，我会再去看看。在那之前，等我有时间了，我真的很想花点时间在 MXNet 上，因为《动手学深度学习》这本书看起来确实很不错。

  …some nodes and split others, maybe that's easy in PyTorch. If that's the case, I'll take a second look. Until then, when I have some time, I'm really tempted to invest some time in MXNet, as the book "Dive into Deep Learning" appears to be quite good.

• nextos · 2023 年

  没有任何关联，但我一直觉得 https://d2l.ai 是严谨性和可运行代码的绝佳结合。

  Not affiliated in any way, but I have always found https://d2l.ai a pretty good mix of rigor and working code.

• ShradhaSingh · 2020 年

  https://d2l.ai/chapter_optimization/index.html

• KorfmannArno · 2020 年

  《动手学深度学习》（Dive Into Deep Learning）- d2l.ai

  "Dive Into Deep Learning" - d2l.ai

正在加载完整评论……