Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 29f5b4f

Browse files
author
xyliao
committed
fix word embedding bug
1 parent 9defba8 commit 29f5b4f

File tree

2 files changed

+7
-7
lines changed

2 files changed

+7
-7
lines changed

‎chapter5_RNN/nlp/word-embedding.ipynb‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -28,19 +28,19 @@
2828
"source": [
2929
"我们举一个例子,下面有 4 段话\n",
3030
"\n",
31-
"1. The cat likes playing ball.\n",
31+
"1. The cat likes playing wool.\n",
3232
"\n",
3333
"2. The kitty likes playing wool.\n",
3434
"\n",
3535
"3. The dog likes playing ball.\n",
3636
"\n",
37-
"4. The body likes playing ball.\n",
37+
"4. The boy does not like playing ball or wool.\n",
3838
"\n",
39-
"这里面有 4 个词,分别是 cat, kitty, dog 和 boy。下面我们使用一个二维的词向量 (a, b) 来表示每一个词,其中 a,b 分别代表着这个词的一种属性,比如 a 代表是否喜欢玩飞盘,b 代表是否喜欢玩毛线,数值越大表示越喜欢,那么我们就能够用数值来定义每一个单词。\n",
39+
"这里面有 4 个词,分别是 cat, kitty, dog 和 boy。下面我们使用一个二维的词向量 (a, b) 来表示每一个词,其中 a,b 分别代表着这个词的一种属性,比如 a 代表是否喜欢玩球,b 代表是否喜欢玩毛线,数值越大表示越喜欢,那么我们就能够用数值来定义每一个单词。\n",
4040
"\n",
41-
"对于 cat,我们可以定义它的词嵌入为 (-1, 4),因为他不喜欢玩飞盘,喜欢玩毛线,同时可以定义 kitty 为 (-2, 5),dog 为 (3, 2) 以及 boy 为 (-2, -3),那么把这四个向量在坐标系中表示出来,就是\n",
41+
"对于 cat,我们可以定义它的词嵌入为 (-1, 4),因为他不喜欢玩球,喜欢玩毛线,同时可以定义 kitty 为 (-2, 5),dog 为 (3, 2) 以及 boy 为 (-2, -3),那么把这四个向量在坐标系中表示出来,就是\n",
4242
"\n",
43-
"![](https://ws1.sinaimg.cn/large/006tNc79gy1fmwf2jxhbzj30g40b2my2.jpg)"
43+
"<img src=\"https://ws1.sinaimg.cn/large/006tNc79gy1fmwf2jxhbzj30g40b2my2.jpg\" width=\"350\">"
4444
]
4545
},
4646
{

‎chapter6_GAN/gan.ipynb‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1200,7 +1200,7 @@
12001200
" logits_real = D_net(real_data) # 判别网络得分\n",
12011201
" \n",
12021202
" sample_noise = (torch.rand(bs, noise_size) - 0.5) / 0.5 # -1 ~ 1 的均匀分布\n",
1203-
" g_fake_seed = Variable(sample_noise).cuda(1)\n",
1203+
" g_fake_seed = Variable(sample_noise).cuda()\n",
12041204
" fake_images = G_net(g_fake_seed) # 生成的假的数据\n",
12051205
" logits_fake = D_net(fake_images) # 判别网络得分\n",
12061206
"\n",
@@ -1423,7 +1423,7 @@
14231423
"name": "python",
14241424
"nbconvert_exporter": "python",
14251425
"pygments_lexer": "ipython3",
1426-
"version": "3.6.2"
1426+
"version": "3.6.3"
14271427
}
14281428
},
14291429
"nbformat": 4,

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /