課程信息
4.8
126 個評分
19 個審閱

100% 在線

立即開始,按照自己的計劃學習。

可靈活調整截止日期

根據您的日程表重置截止日期。

中級

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

完成時間大約為6 小時

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

英語(English)

字幕:英語(English)

您將學到的內容有

  • 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

您將獲得的技能

Inductive TransferAugmentationDropoutsMachine LearningTensorflow

100% 在線

立即開始,按照自己的計劃學習。

可靈活調整截止日期

根據您的日程表重置截止日期。

中級

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

完成時間大約為6 小時

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

英語(English)

字幕:英語(English)

教學大綱 - 您將從這門課程中學到什麼

1
完成時間為 4 小時

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 個視頻 (總計 18 分鐘), 6 個閱讀材料, 3 個測驗
8 個視頻
A conversation with Andrew Ng1分鐘
Training with the cats vs. dogs dataset2分鐘
Working through the notebook4分鐘
Fixing through cropping49
Visualizing the effect of the convolutions1分鐘
Looking at accuracy and loss1分鐘
Week 1 Outro33
6 個閱讀材料
Before you Begin: TensorFlow 2.0 and this Course10分鐘
The cats vs dogs dataset10分鐘
Looking at the notebook10分鐘
What you'll see next10分鐘
What have we seen so far?10分鐘
Getting ready for the exercise10分鐘
1 個練習
Week 1 Quiz30分鐘
2
完成時間為 4 小時

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 個視頻 (總計 14 分鐘), 7 個閱讀材料, 3 個測驗
7 個視頻
Introducing augmentation2分鐘
Coding augmentation with ImageDataGenerator3分鐘
Demonstrating overfitting in cats vs. dogs1分鐘
Adding augmentation to cats vs. dogs1分鐘
Exploring augmentation with horses vs. humans1分鐘
Week 2 Outro37
7 個閱讀材料
Image Augmentation10分鐘
Start Coding...10分鐘
Looking at the notebook10分鐘
The impact of augmentation on Cats vs. Dogs10分鐘
Try it for yourself!10分鐘
What have we seen so far?10分鐘
Getting ready for the exercise10分鐘
1 個練習
Week 2 Quiz30分鐘
3
完成時間為 4 小時

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 個視頻 (總計 14 分鐘), 6 個閱讀材料, 3 個測驗
7 個視頻
Understanding transfer learning: the concepts2分鐘
Coding transfer learning from the inception mode1分鐘
Coding your own model with transferred features2分鐘
Exploring dropouts1分鐘
Exploring Transfer Learning with Inception1分鐘
Week 3 Outro36
6 個閱讀材料
Start coding!10分鐘
Adding your DNN10分鐘
Using dropouts!10分鐘
Applying Transfer Learning to Cats v Dogs10分鐘
What have we seen so far?10分鐘
Getting ready for the exercise10分鐘
1 個練習
Week 3 Quiz30分鐘
4
完成時間為 4 小時

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 個視頻 (總計 12 分鐘), 6 個閱讀材料, 3 個測驗
6 個視頻
Moving from binary to multi-class classification44
Explore multi-class with Rock Paper Scissors dataset2分鐘
Train a classifier with Rock Paper Scissors1分鐘
Test the Rock Paper Scissors classifier2分鐘
Outro, A conversation with Andrew Ng1分鐘
6 個閱讀材料
Introducing the Rock-Paper-Scissors dataset10分鐘
Check out the code!10分鐘
Try testing the classifier10分鐘
What have we seen so far?10分鐘
Getting ready for the exercise10分鐘
Outro10分鐘
1 個練習
Week 4 Quiz30分鐘
4.8
19 個審閱Chevron Right

熱門審閱

創建者 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.

創建者 RCMay 15th 2019

Excellent material superbly presented by world-class experts.\n\nSorry if this sounds sycophantic, but this series contains some of the best courses I've encountered in50+ years of learning.

講師

Avatar

Laurence Moroney

AI Advocate
Google Brain

關於 deeplearning.ai

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

常見問題

  • 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。

還有其他問題嗎?請訪問 學生幫助中心