Skip to content

Commit

Permalink
Qrcode for CH8, Introduction, Installation, Notation & Preface (d2l-a…
Browse files Browse the repository at this point in the history
…i#670)

* qr code

* chapter 8 qrcode
  • Loading branch information
goldmermaid authored Feb 23, 2021
1 parent 3f8dd46 commit 602b53c
Show file tree
Hide file tree
Showing 11 changed files with 34 additions and 24 deletions.
6 changes: 3 additions & 3 deletions chapter_installation/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -128,13 +128,13 @@ pip install mxnet-cu101==1.7.0
1. 下载该书的代码并安装运行时环境。

:begin_tab:`mxnet`
[Discussions](https://discuss.d2l.ai/t/23)
[Discussions](https://discuss.d2l.ai/t/2082)
:end_tab:

:begin_tab:`pytorch`
[Discussions](https://discuss.d2l.ai/t/24)
[Discussions](https://discuss.d2l.ai/t/2083)
:end_tab:

:begin_tab:`tensorflow`
[Discussions](https://discuss.d2l.ai/t/436)
[Discussions](https://discuss.d2l.ai/t/2084)
:end_tab:
2 changes: 1 addition & 1 deletion chapter_introduction/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -752,4 +752,4 @@ Canny边缘检测器 :cite:`Canny.1987` 和SIFT特征提取器 :cite:`Lowe.2004`
1. 如果把人工智能的发展看作一场新的工业革命,那么算法和数据之间的关系是什么?它类似于蒸汽机和煤吗?根本区别是什么?
1. 你还可以在哪里应用端到端的训练方法,比如 :numref:`fig_ml_loop` 、物理、工程和计量经济学?

[Discussions](https://discuss.d2l.ai/t/22)
[Discussions](https://discuss.d2l.ai/t/2088)
2 changes: 1 addition & 1 deletion chapter_notation/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -70,4 +70,4 @@

* $\mathcal{O}$:大O标记

[Discussions](https://discuss.d2l.ai/t/25)
[Discussions](https://discuss.d2l.ai/t/2089)
6 changes: 3 additions & 3 deletions chapter_preface/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -157,13 +157,13 @@ import tensorflow as tf
1. 点击论坛部分底部的链接,您将能够寻求帮助和讨论这本书,并通过吸引作者和更广泛的社区来找到问题的答案。

:begin_tab:`mxnet`
[Discussions](https://discuss.d2l.ai/t/18)
[Discussions](https://discuss.d2l.ai/t/2085)
:end_tab:

:begin_tab:`pytorch`
[Discussions](https://discuss.d2l.ai/t/20)
[Discussions](https://discuss.d2l.ai/t/2086)
:end_tab:

:begin_tab:`tensorflow`
[Discussions](https://discuss.d2l.ai/t/186)
[Discussions](https://discuss.d2l.ai/t/2087)
:end_tab:
2 changes: 1 addition & 1 deletion chapter_recurrent-neural-networks/bptt.md
Original file line number Diff line number Diff line change
Expand Up @@ -164,4 +164,4 @@ $$
1. 上述结果对于循环神经网络中的梯度意味着什么?
1. 除了梯度裁剪,你还能想到其他方法来应对循环神经网络中的梯度爆炸吗?

[Discussions](https://discuss.d2l.ai/t/334)
[Discussions](https://discuss.d2l.ai/t/2107)
Original file line number Diff line number Diff line change
Expand Up @@ -288,13 +288,13 @@ def load_data_time_machine(batch_size, num_steps, #@save
1. 如果我们希望一个序列样本是一个完整的句子,那么这在小批量抽样中会带来什么样的问题呢?我们怎样才能解决这个问题呢?

:begin_tab:`mxnet`
[Discussions](https://discuss.d2l.ai/t/117)
[Discussions](https://discuss.d2l.ai/t/2096)
:end_tab:

:begin_tab:`pytorch`
[Discussions](https://discuss.d2l.ai/t/118)
[Discussions](https://discuss.d2l.ai/t/2097)
:end_tab:

:begin_tab:`tensorflow`
[Discussions](https://discuss.d2l.ai/t/1049)
[Discussions](https://discuss.d2l.ai/t/2098)
:end_tab:
4 changes: 2 additions & 2 deletions chapter_recurrent-neural-networks/rnn-concise.md
Original file line number Diff line number Diff line change
Expand Up @@ -187,9 +187,9 @@ d2l.train_ch8(net, train_iter, vocab, lr, num_epochs, device)
1. 使用循环神经网络实现 :numref:`sec_sequence` 的自回归模型。

:begin_tab:`mxnet`
[Discussions](https://discuss.d2l.ai/t/335)
[Discussions](https://discuss.d2l.ai/t/2105)
:end_tab:

:begin_tab:`pytorch`
[Discussions](https://discuss.d2l.ai/t/1053)
[Discussions](https://discuss.d2l.ai/t/2106)
:end_tab:
6 changes: 3 additions & 3 deletions chapter_recurrent-neural-networks/rnn-scratch.md
Original file line number Diff line number Diff line change
Expand Up @@ -680,13 +680,13 @@ train_ch8(net, train_random_iter, vocab_random_iter, num_hiddens, lr,
1. 用ReLU替换本节中使用的激活函数,并重复本节中的实验。我们还需要梯度裁剪吗?为什么?

:begin_tab:`mxnet`
[Discussions](https://discuss.d2l.ai/t/336)
[Discussions](https://discuss.d2l.ai/t/2102)
:end_tab:

:begin_tab:`pytorch`
[Discussions](https://discuss.d2l.ai/t/486)
[Discussions](https://discuss.d2l.ai/t/2103)
:end_tab:

:begin_tab:`tensorflow`
[Discussions](https://discuss.d2l.ai/t/1052)
[Discussions](https://discuss.d2l.ai/t/2104)
:end_tab:
6 changes: 3 additions & 3 deletions chapter_recurrent-neural-networks/rnn.md
Original file line number Diff line number Diff line change
Expand Up @@ -154,13 +154,13 @@ $$\exp\left(-\frac{1}{n} \sum_{t=1}^n \log P(x_t \mid x_{t-1}, \ldots, x_1)\righ
1. 与本节中描述的语言模型相关的问题有哪些?

:begin_tab:`mxnet`
[Discussions](https://discuss.d2l.ai/t/337)
[Discussions](https://discuss.d2l.ai/t/2099)
:end_tab:

:begin_tab:`pytorch`
[Discussions](https://discuss.d2l.ai/t/1050)
[Discussions](https://discuss.d2l.ai/t/2100)
:end_tab:

:begin_tab:`tensorflow`
[Discussions](https://discuss.d2l.ai/t/1051)
[Discussions](https://discuss.d2l.ai/t/2101)
:end_tab:
6 changes: 3 additions & 3 deletions chapter_recurrent-neural-networks/sequence.md
Original file line number Diff line number Diff line change
Expand Up @@ -365,13 +365,13 @@ d2l.plot([time[tau + i - 1: T - max_steps + i] for i in steps],
1. 举例说明什么时候可能需要隐变量自回归模型来捕捉数据的动力学模型。

:begin_tab:`mxnet`
[Discussions](https://discuss.d2l.ai/t/113)
[Discussions](https://discuss.d2l.ai/t/2090)
:end_tab:

:begin_tab:`pytorch`
[Discussions](https://discuss.d2l.ai/t/114)
[Discussions](https://discuss.d2l.ai/t/2091)
:end_tab:

:begin_tab:`tensorflow`
[Discussions](https://discuss.d2l.ai/t/1048)
[Discussions](https://discuss.d2l.ai/t/2092)
:end_tab:
12 changes: 11 additions & 1 deletion chapter_recurrent-neural-networks/text-preprocessing.md
Original file line number Diff line number Diff line change
Expand Up @@ -167,4 +167,14 @@ len(corpus), len(vocab)
1. 标记化是一个关键的预处理步骤。它因语言而异。尝试找到另外三种常用的文本标记方法。
1. 在本节的实验中,将文本标记为单词,并更改`Vocab`实例的`min_freq`参数。这对词汇量有何影响?

[Discussions](https://discuss.d2l.ai/t/115)
:begin_tab:`mxnet`
[Discussions](https://discuss.d2l.ai/t/2093)
:end_tab:

:begin_tab:`pytorch`
[Discussions](https://discuss.d2l.ai/t/2094)
:end_tab:

:begin_tab:`tensorflow`
[Discussions](https://discuss.d2l.ai/t/2095)
:end_tab:

0 comments on commit 602b53c

Please sign in to comment.