Lightning AI Studios: Never set up a local environment again →

Log in or create a free Lightning.ai account to track your progress and access additional course materials  

Deep Learning Fundamentals

  • Pages

    • Final certification exam

    Deep Learning Fundamentals > Unit 7 > Unit 7.1
    Course Progress:

    Unit 7.1 – Working With Images

    Slides

    Manual feature extraction involves converting images into tables before feeding these to a multilayer perceptron. This is no longer necessary when we work with convolutional networks, which implicitely utilize automatic feature extraction methods to accomplish this task. In other words, convolutional layers serve as efficient feature extractors for RGB color images.

    Log in or create a free Lightning.ai account to access:

    • Quizzes
    • Completion badges
    • Progress tracking
    • Additional downloadable content
    • Additional AI education resources
    • Notifications when new units are released
    • Free cloud computing credits

    Quiz: 7.1 Working With Images - Part 1

    If we work with a quadratic color image that has 224 pixels on one side, how many pixels is that in total?

    Incorrect. This would be a line, not an image.

    Incorrect. Did you forget the color channels?

    Incorrect. The number of pixels in a channel is not 224×2.

    Correct. A quadratic color image with 3 color channels has 224x224x3 pixels

    Please answer all questions to proceed.

    Quiz: 7.1 Working With Images - Part 2

    In the video, we concatenated the image pixels row by row to represent an image as a table for a conventional machine learning classifier and multilayer perceptron. Could we do this concatenation column-by-column instead?

    Correct. It does not matter whether as long as we are consistent.

    Incorrect. It does not matter whether as long as we are consistent.

    Please answer all questions to proceed.
    Watch Video 1

    Unit 7.1

    Videos
    Follow along in a Lightning Studio

    DL Fundamentals 7: Computer Vision

    Sebastian
    Launch Studio →