Completed
- Data augmentation & preprocessing another way to improve performance
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Solving Real World Data Science Problems With Python - Computer Vision Edition
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro
- 2 - Video overview what we’ll be working on
- 3 - Code setup GitHub repo & HP challenge link
- 4 - Exploring the dataset that we’ll be using
- 5 - Reviewing template code starter-code.ipynb
- 6 - Installing necessary Python libraries opencv-python, tensorflow
- 7 - Reviewing template code part 2
- 8 - How we load in the dataset ImageDataGenerator, flow_from_directory
- 9 - Building our first classifier convolutional neural net - CNN
- 10 - Methods to improve neural network performance MaxPooling, dropout, network architecture
- 11 - Quick discussion about importance of precision & recall versus accuracy
- 12 - Data augmentation & preprocessing another way to improve performance
- 13 - Programmatically finding the best neural network architectures Keras Tuner
- 14 - Video recap & conclusion
