课程信息
240,781 次近期查看

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

Course 1 of the TensorFlow Specialization, Python coding, and high-school level math are required. ML/DL experience is helpful but not required.

完成时间大约为6 小时

建议:4 weeks of study, 4-5 hours/week...

英语(English)

字幕:英语(English)

您将学到的内容有

  • Check

    Handle real-world image data

  • Check

    Plot loss and accuracy

  • Check

    Explore strategies to prevent overfitting, including augmentation and dropout

  • Check

    Learn transfer learning and how learned features can be extracted from models

您将获得的技能

Inductive TransferAugmentationDropoutsMachine LearningTensorflow

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

Course 1 of the TensorFlow Specialization, Python coding, and high-school level math are required. ML/DL experience is helpful but not required.

完成时间大约为6 小时

建议:4 weeks of study, 4-5 hours/week...

英语(English)

字幕:英语(English)

教学大纲 - 您将从这门课程中学到什么

1
完成时间为 4 小时

Exploring a Larger Dataset

In the first course in this specialization, you had an introduction to TensorFlow, and how, with its high level APIs you could do basic image classification, an you learned a little bit about Convolutional Neural Networks (ConvNets). In this course you'll go deeper into using ConvNets will real-world data, and learn about techniques that you can use to improve your ConvNet performance, particularly when doing image classification! In Week 1, this week, you'll get started by looking at a much larger dataset than you've been using thus far: The Cats and Dogs dataset which had been a Kaggle Challenge in image classification!...
8 个视频 (总计 18 分钟), 6 个阅读材料, 3 个测验
8 个视频
A conversation with Andrew Ng1分钟
Training with the cats vs. dogs dataset2分钟
Working through the notebook4分钟
Fixing through cropping49
Visualizing the effect of the convolutions1分钟
Looking at accuracy and loss1分钟
Week 1 Outro33
6 个阅读材料
Before you Begin: TensorFlow 2.0 and this Course10分钟
The cats vs dogs dataset10分钟
Looking at the notebook10分钟
What you'll see next10分钟
What have we seen so far?10分钟
Getting ready for the exercise10分钟
1 个练习
Week 1 Quiz30分钟
2
完成时间为 4 小时

Augmentation: A technique to avoid overfitting

You've heard the term overfitting a number of times to this point. Overfitting is simply the concept of being over specialized in training -- namely that your model is very good at classifying what it is trained for, but not so good at classifying things that it hasn't seen. In order to generalize your model more effectively, you will of course need a greater breadth of samples to train it on. That's not always possible, but a nice potential shortcut to this is Image Augmentation, where you tweak the training set to potentially increase the diversity of subjects it covers. You'll learn all about that this week!...
7 个视频 (总计 14 分钟), 7 个阅读材料, 3 个测验
7 个视频
Introducing augmentation2分钟
Coding augmentation with ImageDataGenerator3分钟
Demonstrating overfitting in cats vs. dogs1分钟
Adding augmentation to cats vs. dogs1分钟
Exploring augmentation with horses vs. humans1分钟
Week 2 Outro37
7 个阅读材料
Image Augmentation10分钟
Start Coding...10分钟
Looking at the notebook10分钟
The impact of augmentation on Cats vs. Dogs10分钟
Try it for yourself!10分钟
What have we seen so far?10分钟
Getting ready for the exercise10分钟
1 个练习
Week 2 Quiz30分钟
3
完成时间为 4 小时

Transfer Learning

Building models for yourself is great, and can be very powerful. But, as you've seen, you can be limited by the data you have on hand. Not everybody has access to massive datasets or the compute power that's needed to train them effectively. Transfer learning can help solve this -- where people with models trained on large datasets train them, so that you can either use them directly, or, you can use the features that they have learned and apply them to your scenario. This is Transfer learning, and you'll look into that this week!...
7 个视频 (总计 14 分钟), 6 个阅读材料, 3 个测验
7 个视频
Understanding transfer learning: the concepts2分钟
Coding transfer learning from the inception mode1分钟
Coding your own model with transferred features2分钟
Exploring dropouts1分钟
Exploring Transfer Learning with Inception1分钟
Week 3 Outro36
6 个阅读材料
Start coding!10分钟
Adding your DNN10分钟
Using dropouts!10分钟
Applying Transfer Learning to Cats v Dogs10分钟
What have we seen so far?10分钟
Getting ready for the exercise10分钟
1 个练习
Week 3 Quiz30分钟
4
完成时间为 4 小时

Multiclass Classifications

You've come a long way, Congratulations! One more thing to do before we move off of ConvNets to the next module, and that's to go beyond binary classification. Each of the examples you've done so far involved classifying one thing or another -- horse or human, cat or dog. When moving beyond binary into Categorical classification there are some coding considerations you need to take into account. You'll look at them this week!...
6 个视频 (总计 12 分钟), 6 个阅读材料, 3 个测验
6 个视频
Moving from binary to multi-class classification44
Explore multi-class with Rock Paper Scissors dataset2分钟
Train a classifier with Rock Paper Scissors1分钟
Test the Rock Paper Scissors classifier2分钟
Outro, A conversation with Andrew Ng1分钟
6 个阅读材料
Introducing the Rock-Paper-Scissors dataset10分钟
Check out the code!10分钟
Try testing the classifier10分钟
What have we seen so far?10分钟
Getting ready for the exercise10分钟
Outro10分钟
1 个练习
Week 4 Quiz30分钟
4.8
23 个审阅Chevron Right

热门审阅

创建者 MHMay 24th 2019

A very comprehensive and easy to learn course on Tensor Flow. I am really impressed by the Instructor ability to teach difficult concept with ease. I will look forward another course of this series.

创建者 CMMay 1st 2019

A patient and coherent introduction. At the end, you have good working code you can use elsewhere. Remarkably, the primary lecturer, Laurence Moroney, responds fairly quickly to posts in the forum.

讲师

Avatar

Laurence Moroney

AI Advocate
Google Brain

关于 deeplearning.ai

deeplearning.ai is Andrew Ng's new venture which amongst others, strives for providing comprehensive AI education beyond borders....

常见问题

  • 注册以便获得证书后,您将有权访问所有视频、测验和编程作业(如果适用)。只有在您的班次开课之后,才可以提交和审阅同学互评作业。如果您选择在不购买的情况下浏览课程,可能无法访问某些作业。

  • 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。

还有其他问题吗?请访问 学生帮助中心