We’ll use PyTorch for traditional coding approaches, but we’ll also introduce low-code and no-code options to make computer vision accessible to a broader audience. This dual approach ensures that both experienced programmers and those new to coding can benefit from the course. We’ve included quizzes to test your understanding and assignments to apply your knowledge to real-world applications. By the end of this course, you’ll have the skills and confidence to tackle complex computer vision challenges using both traditional coding and modern low-code/no-code tools.
End-to-End Computer Vision
November 3 @ 8:00 am – December 15 @ 5:00 pm
Course Description
This End-to-End Computer Vision course will explore how computers understand and process images. We’ll cover key topics from image classification to object detection and segmentation, providing you with practical skills to build, train, and deploy computer vision models. Through interactive lessons and hands-on projects, you’ll gain the expertise to create end-to-end solutions for real-world problems in AI and machine learning.
Course at a Glance
Mastering PyTorch
End-to-End Computer Vision
End-to-End Natural Language Processing
Generative Models
MLOps
Interpretability in AI
Prerequisites:
Basic Python & PyTorch programming
Basic understanding of deep learning
By the end of the course, you should be able to:
- 1. 3 Quizzes: Test comprehension of fundamental computer vision concepts.
- 2. 1 Coding Assignment: Implement solutions for image classification, object detection, and segmentation using PyTorch. Tasks include fine-tuning models, data preprocessing, and deployment.
- Module 1: Introduction to Computer Vision
- Computer vision fundamentals and industry applications
- Types of computer vision tasks (classification, detection, segmentation)
- Visual data types: 2D images, hyperspectral images, 3D point clouds
- Computer vision pipeline: data collection → model training → evaluation → deployment
- Module 2: Computer Vision Data Handling
- Image preprocessing techniques and data augmentation
- Data annotation for object detection, segmentation, and keypoint tasks
- PyTorch DataLoader implementation and efficient data loading pipelines
- Dataset preparation strategies and annotation tools
- Module 3: Computer Vision Model Architectures
- CNN fundamentals and classic architectures (AlexNet, VGG, ResNet)
- Transfer learning and fine-tuning strategies
- Advanced architectures for object detection (YOLO, SSD, Faster R-CNN)
- Segmentation models (U-Net, Mask R-CNN) and modern loss functions
- Module 4: Model Training, Optimization, and Modern Architectures
- Advanced training techniques and optimization strategies
- Model explainability and interpretation methods
- State-of-the-art object detection and segmentation models
- Transformer-based and multimodal vision models
- Model deployment, quantization, and no-code/low-code frameworks
- The course starts on November 1, 2025. All coursework must be completed by December 15, 2025 (with possible extension for industry professionals only), in order to earn the micro-credential badge. You will continue to have access to the course materials until January 15, 2026. The approximate time to complete this course is 16 hours.
- This course has an instructional period from November 1 to December 7, 2025. During this instructional period, course materials will be released weekly, and live synchronous sessions will be held. You may complete the course materials at your own pace. Live Zoom meetings will be conducted for interactive coding sessions and answering any questions you have.
- You will receive the micro-credential badge upon successful completion of the course assessments.
- Course Materials:
- Course materials are provided within the course. No additional purchase is required.
Students
Industry Professionals/ISU Staff/Post Docs
$
500
.00