Deep Learning: Advanced Computer Vision
  • ondemand_video
       Video Length : 9h10m0s
  • format_list_bulleted
       Tasks Number : 63
  • group
       Students Enrolled : 1032
  • equalizer
       Medium Level
  • Curriculum
  • 1. Welcome
    • videocam
      Introduction
      10m0s
    • videocam
      Outline and Perspective
      10m0s
    • videocam
      How to Succeed in this Course
      10m0s
  • 2. Review
    • videocam
      Review of CNNs
      10m0s
    • videocam
      Where to get the code and data
      10m0s
    • videocam
      Fashion MNIST
      10m0s
    • videocam
      Review of CNNs in Code
      10m0s
  • 3. VGG and Transfer Learning
    • videocam
      VGG Section Intro
      10m0s
    • videocam
      What's so special about VGG?
      10m0s
    • videocam
      Transfer Learning
      10m0s
    • videocam
      Relationship to Greedy Layer-Wise Pretraining
      10m0s
    • videocam
      Getting the data
      10m0s
    • videocam
      Code pt 1
      10m0s
    • videocam
      Code pt 2
      10m0s
    • videocam
      Code pt 3
      10m0s
    • videocam
      VGG Section Summary
      10m0s
  • 4. ResNet (and Inception)
    • videocam
      ResNet Section Intro
      10m0s
    • videocam
      ResNet Architecture
      10m0s
    • videocam
      Building ResNet - Strategy
      10m0s
    • videocam
      Building ResNet - Conv Block Details
      10m0s
    • videocam
      Building ResNet - Conv Block Code
      10m0s
    • videocam
      Building ResNet - Identity Block Details
      10m0s
    • videocam
      Building ResNet - First Few Layers
      10m0s
    • videocam
      Building ResNet - First Few Layers (Code)
      10m0s
    • videocam
      Building ResNet - Putting it all together
      10m0s
    • videocam
      Exercise: Apply ResNet
      10m0s
    • videocam
      Applying ResNet
      10m0s
    • videocam
      1x1 Convolutions
      10m0s
    • videocam
      Optional: Inception
      10m0s
    • videocam
      Different sized images using the same network
      10m0s
    • videocam
      ResNet Section Summary
      10m0s
  • 5. Object Detection (SSD)
    • videocam
      SSD Section Intro
      10m0s
    • videocam
      Object Localization
      10m0s
    • videocam
      What is Object Detection?
      10m0s
    • videocam
      How would you find an object in an image?
      10m0s
    • videocam
      The Problem of Scale
      10m0s
    • videocam
      The Problem of Shape
      10m0s
    • videocam
      SSD in Tensorflow
      10m0s
    • videocam
      Modifying SSD to work on Video
      10m0s
    • videocam
      Optional: Intersection over Union & Non-max Suppression
      10m0s
    • videocam
      SSD Section Summary
      10m0s
  • 6. Neural Style Transfer
    • videocam
      Style Transfer Section Intro
      10m0s
    • videocam
      Style Transfer Theory
      10m0s
    • videocam
      Optimizing the Loss
      10m0s
    • videocam
      Code pt 1
      10m0s
    • videocam
      Code pt 2
      10m0s
    • videocam
      Code pt 3
      10m0s
    • videocam
      Style Transfer Section Summary
      10m0s
  • 7. Bonus: Class Activation Maps
    • videocam
      Class Activation Maps (Theory)
      10m0s
    • videocam
      Class Activation Maps (Code)
      10m0s
  • 8. Basics Review
    • videocam
      Tensorflow Basics
      10m0s
    • videocam
      Tensorflow Neural Network in Code
      10m0s
    • videocam
      Keras Discussion
      10m0s
    • videocam
      Keras Neural Network in Code
      10m0s
    • videocam
      Keras Functional API
      10m0s
Authors

Kevin Gautama is a systems design and programming engineer with 16 years of expertise in the fields of electrical and electronics and information technology.

He teaches at the Hanoi University of Industry in the period 2003-2011 and he has a certificate of vocational training by the Ministry of Industry and Commerce and the Hanoi University of Industry.

From extensive design experience through numerous engineering projects, the author founded the Enziin Academy.

The Enziin Academy is a startup in the field of educational, it's core goal is to training design engineers in the fields technology related.

The Enziin Academy is headquartered in Stockholm-Sweden with an orientation operating multi-lingual and global.

The author's skills in IT:

  • Implementing the application infrastructure on Amazon's cloud computing platform.
  • Linux server system administration (Sysadmin).
  • Design load balancing and content distribution system.
  • MySQL database administration.
  • C/C++/C# Programming
  • Ruby and Ruby on Rails Programming
  • Python and Django Programming
  • The WPF/C# on the .NET Framework Programming
  • The PHP/JAVA Programming
  • Machine Learning and Expert System.
  • Internet of Things.

The author's skills in the fields of electric and electronic:

  • The design of popular CPU / MCU systems.
  • Design FPGA / CPLD system (Xilinx - Altera).
  • Design and programming of DSP systems (Texas Instruments).
  • Embedded ARM system design.
  • The RTOS Programming
  • Design and programming electronic power systems.
  • PLC - inverter - sensor - electric control cabinet industrial.
  • Control systems distributed connection with Server.

Read more...

Deep Learning: Advanced Computer Vision


Deep Learning: Advanced Computer Vision

Discussions
You must login to comment.