课程信息

45,910 次近期查看
可分享的证书
完成后获得证书
100% 在线
立即开始,按照自己的计划学习。
可灵活调整截止日期
根据您的日程表重置截止日期。
中级
完成时间大约为27 小时
英语(English)
字幕:英语(English)
可分享的证书
完成后获得证书
100% 在线
立即开始,按照自己的计划学习。
可灵活调整截止日期
根据您的日程表重置截止日期。
中级
完成时间大约为27 小时
英语(English)
字幕:英语(English)

提供方

伦敦帝国学院 徽标

伦敦帝国学院

教学大纲 - 您将从这门课程中学到什么

1

1

完成时间为 6 小时

The Keras functional API

完成时间为 6 小时
14 个视频 (总计 81 分钟), 5 个阅读材料, 2 个测验
14 个视频
Interview with Laurence Moroney4分钟
The Keras functional API5分钟
Multiple inputs and outputs6分钟
[Coding tutorial] Multiple inputs and outputs9分钟
Variables5分钟
Tensors5分钟
[Coding tutorial] Variables and Tensors8分钟
Accessing layer Variables4分钟
Accessing layer Tensors5分钟
[Coding tutorial] Accessing model layers8分钟
Freezing layers4分钟
[Coding tutorial] Freezing layers7分钟
Wrap up and introduction to the programming assignment1分钟
5 个阅读材料
About Imperial College & the team10分钟
How to be successful in this course10分钟
Grading policy10分钟
Additional readings & helpful references10分钟
Device placement10分钟
1 个练习
[Knowledge check] Transfer learning10分钟
2

2

完成时间为 6 小时

Data Pipeline

完成时间为 6 小时
12 个视频 (总计 93 分钟), 1 个阅读材料, 2 个测验
12 个视频
Keras datasets3分钟
[Coding tutorial] Keras datasets11分钟
Dataset generators7分钟
[Coding tutorial] Dataset generators12分钟
Keras image data augmentation5分钟
[Coding tutorial] Keras image data augmentation10分钟
The Dataset class8分钟
[Coding tutorial] The Dataset class10分钟
Training with Datasets7分钟
[Coding tutorial] Training with Datasets11分钟
Wrap up and introduction to the programming assignment1分钟
1 个阅读材料
TensorFlow Datasets10分钟
1 个练习
[Knowledge check] Python generators15分钟
3

3

完成时间为 6 小时

Sequence Modelling

完成时间为 6 小时
13 个视频 (总计 92 分钟)
13 个视频
Interview with Doug Kelly10分钟
Preprocessing sequence data7分钟
[Coding tutorial] The IMDB dataset8分钟
[Coding tutorial] Padding and masking sequence data7分钟
The Embedding layer4分钟
[Coding tutorial] The Embedding layer4分钟
[Coding tutorial] The Embedding Projector12分钟
Recurrent neural network layers4分钟
[Coding tutorial] Recurrent neural network layers9分钟
Stacked RNNs and the Bidirectional wrapper7分钟
[Coding tutorial] Stacked RNNs and the Bidirectional wrapper10分钟
Wrap up and introduction to the programming assignment1分钟
1 个练习
[Knowledge check] Recurrent neural networks15分钟
4

4

完成时间为 6 小时

Model subclassing and custom training loops

完成时间为 6 小时
12 个视频 (总计 71 分钟)
12 个视频
Model subclassing5分钟
[Coding tutorial] Model subclassing5分钟
Custom layers7分钟
[Coding tutorial] Custom layers10分钟
Automatic differentiation5分钟
[Coding tutorial] Automatic differentiation6分钟
Custom training loops7分钟
[Coding tutorial] Custom training loops10分钟
tf.function decorator3分钟
[Coding tutorial] tf.function decorator5分钟
Wrap up and introduction to the programming assignment1分钟

审阅

来自CUSTOMISING YOUR MODELS WITH TENSORFLOW 2的热门评论

查看所有评论

常见问题

  • 讲座和作业的访问权限取决于您的注册类型。如果您以旁听模式参加课程,则可以免费查看大多数课程资料。要访问评分作业并获得证书,您需要在旁听期间或之后购买证书体验。如果看不到旁听选项:

    • 课程可能不提供旁听选项。您可以尝试免费试用,也可以申请助学金。
    • 课程可能会改为提供'完整课程,没有证书'。通过此选项,您可以查看所有课程材料、提交所要求的作业,以及获得最终成绩。这也意味着您将无法购买证书体验。
  • 您购买证书后,将有权访问所有课程材料,包括评分作业。完成课程后,您的电子课程证书将添加到您的成就页中,您可以通过该页打印您的课程证书或将其添加到您的领英档案中。如果您只想阅读和查看课程内容,可以免费旁听课程。

  • 您可在付款后两周内,或者在课程第一个班次开课后(对于已启动的课程)两周内,获得全额退款,以其中较晚者为准。获得课程证书后,您便无法再退款;即使您在两周的退款期内完成了课程,也是如此。请阅读我们完整的退款政策

  • 是的,Coursera 可以向无法承担学费的学生提供助学金。点击左侧‘注册’按钮下的‘助学金’链接即可申请助学金。您可以根据屏幕提示完成申请,申请获批后会收到通知。了解详情

  • Jupyter Notebooks are a third-party tool that some Coursera courses use for programming assignments.

    You can revert your code or get a fresh copy of your Jupyter Notebook mid-assignment. By default, Coursera persistently stores your work within each notebook.

    To keep your old work and also get a fresh copy of the initial Jupyter Notebook, click File, then Make a copy.

    We recommend keeping a naming convention such as “Assignment 1 - Initial” or “Copy” to keep your notebook environment organized. You can also download this file locally.

    Refresh your notebook

    1. Rename your existing Jupyter Notebook within the individual notebook view
    2. In the notebook view, add “?forceRefresh=true” to the end of your notebook URL
    3. Reload the screen
    4. You will be directed to your home Learner Workspace where you’ll see both old and new Notebook files.
    5. Your Notebook lesson item will now launch to the fresh notebook.

    Find missing work

    If your Jupyter Notebook files have disappeared, it means the course staff published a new version of a given notebook to fix problems or make improvements. Your work is still saved under the original name of the previous version of the notebook.

    To recover your work:

    1. Find your current notebook version by checking the top of the notebook window for the title
    2. In your Notebook view, click the Coursera logo
    3. Find and click the name of your previous file

    Unsaved work

    "Kernels" are the execution engines behind the Jupyter Notebook UI. As kernels time out after 90 minutes of notebook activity, be sure to save your notebooks frequently to prevent losing any work. If the kernel times out before the save, you may lose the work in your current session.

    How to tell if your kernel has timed out:

    • Error messages such as "Method Not Allowed" appear in the toolbar area.
    • The last save or auto-checkpoint time shown in the title of the notebook window has not updated recently
    • Your cells are not running or computing when you “Shift + Enter”

    To restart your kernel:

    1. Save your notebook locally to store your current progress
    2. In the notebook toolbar, click Kernel, then Restart
    3. Try testing your kernel by running a print statement in one of your notebook cells. If this is successful, you can continue to save and proceed with your work.
    4. If your notebook kernel is still timed out, try closing your browser and relaunching the notebook. When the notebook reopens, you will need to do "Cell -> Run All" or "Cell -> Run All Above" to regenerate the execution state.
  • 此课程不提供大学学分,但部分大学可能会选择接受课程证书作为学分。查看您的合作院校,了解详情。Coursera 上的在线学位Mastertrack™ 证书提供获得大学学分的机会。

还有其他问题吗?请访问 学生帮助中心