Skip to content

Commit

Permalink
code output ideal
Browse files Browse the repository at this point in the history
  • Loading branch information
astonzhang committed Feb 25, 2019
1 parent 93162f8 commit d6ccc8a
Show file tree
Hide file tree
Showing 3 changed files with 4 additions and 0 deletions.
1 change: 1 addition & 0 deletions chapter_computational-performance/multiple-gpus-gluon.md
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,7 @@ train(num_gpus=2, batch_size=512, lr=0.2)

* 在Gluon中,可以很方便地进行多GPU计算,例如,在多GPU及相应的显存上初始化模型参数和训练模型。


## 练习

* 本节使用了ResNet-18模型。试试不同的迭代周期、批量大小和学习率。如果条件允许,使用更多GPU来计算。
Expand Down
2 changes: 2 additions & 0 deletions chapter_computer-vision/kaggle-gluon-cifar10.md
Original file line number Diff line number Diff line change
Expand Up @@ -325,6 +325,8 @@ df.to_csv('submission.csv', index=False)

执行完上述代码后,我们会得到一个submission.csv文件。这个文件符合Kaggle比赛要求的提交格式。提交结果的方法与[“实战Kaggle比赛:房价预测”](../chapter_deep-learning-basics/kaggle-house-price.md)一节中的类似。



## 小结

* 可以通过创建`ImageFolderDataset`实例来读取含原始图像文件的数据集。
Expand Down
1 change: 1 addition & 0 deletions chapter_natural-language-processing/word2vec-gluon.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
# word2vec的实现


本节是对前两节内容的实践。我们以[“词嵌入(word2vec)”](word2vec.md)一节中的跳字模型和[“近似训练”](approx-training.md)一节中的负采样为例,介绍在语料库上训练词嵌入模型的实现。我们还会介绍一些实现中的技巧,如二次采样(subsampling)。

首先导入实验所需的包或模块。
Expand Down

0 comments on commit d6ccc8a

Please sign in to comment.