Week 4 - Convolutional Neural Networks, Part I

This week you will...

• go deeper into using ConvNets with real-world data and a much larger dataset than those you've been using thus far.

• learn about image augmentation, a technique to avoid overfitting by tweaking the training set to potentially increase the diversity of subjects it covers.

• discuss your project ideas.

Slides

627KB

251113_CNN_Part_I.pdf

PDF

Open

Learning Resources

• Neural Networks Part 8: Image Classification with Convolutional Neural Networks (CNNs) (StatQuest with Josh Starmer, 15 min)

• C4W1L04 Padding (DeepLearningAI, 9:50 min)

• C4W2L10 Data Augmentation (DeepLearningAI, 9:30 min)

• TensorFlow Tutorial 4 - Convolutional Neural Networks with Sequential and Functional API (Aladdin Persson, first 10 min)

• TensorFlow Tutorial 18 - Custom Dataset for Images (Aladdin Persson, first 7 min)

• Data Augmentation - Deep Learning with Tensorflow | Ep. 19 (Kody Simpson, 23 min)

Until next week you should...

• watch this video to get an introduction on transfer learning (8 min)

• watch this video to learn how to implement transfer learning with CNNs (12 min)

• work through this blog to learn about multi-class classification

• complete the exercise assignment in this notebook

• investigate the characteristics of your project's dataset according to the instructions given here

• document your findings on the dataset characteristics according to the instructions of above