Sorry, JavaScript required!

Computer Vision in practice with TensorFlow

Title Computer Vision in practice with TensorFlow
Course code CM587-05-2022-C

Computer vision studies how to make machines "see" the world. It is widely used in AR/VR, Autopilot and self-driving cars and other fields. Its application prospects are unprecedentedly huge. With the rapid development of technology in recent years, computer vision has made breakthroughs. thus we specially set up this course to popularize the application of machine learning/deep learning in computer vision aspect.


  • Introduction to the concepts, foundations and application conditions behind the core technologies of deep learning and computer vision
  • Use real life pictures to practice the main technology of computer vision through the deep learning framework Tensorflow
  • Linear Algebra
  • Python Programming Recap
  • Introduction to Machine Learning & Artificial Intelligence
  • Introduction to TensorFlow structure & Syntaxes
  • Introduction to Neural Network
  • Deep Neural Network + TensorFlow 2.0
  • Convolution Neural Network
  • Refinement and Dataset Preparation for Real Life Image
  • Convolution Neural Network + Transfer Learning
Assessment At least 80% attendance and complete all in-class exercises and assessments.
Target audience Anyone who interested in Computer Vision, Machine Learning, TensorFlow
Class size 12 Full
Instructor CPTTM Appointed Instructor(s)
Handout All training material provided by CPTTM
Instruction language Cantonese (supplemented with English)
Handout language Bilingual in Chinese and English
Duration 21 hours in 7 sessions
Schedule 10:00-13:00, from May 14, 2022 to May 29, 2022 every Saturday, Sunday, plus Jun 4, 2022(Saturday).
Fee MOP2,400
Venue Cyber-Lab (Rua Comandante Mata Oliveira, Ed. Associacao Industrial, 3-andar Macau)
Certificate Certificate of Completion issued by CPTTM (with at least 80% attendance and passed the assessment)
PDAC code Approved Course under the SAR Government "Continuing Education Development Program", Code: 2110190321-0
Sorry, JavaScript required!