Computer Vision with Embedded Machine Learning
4.0 /5- Offered byCoursera
Computer Vision with Embedded Machine Learning at Coursera Overview
Duration | 31 hours |
Start from | Start Now |
Total fee | Free |
Mode of learning | Online |
Difficulty level | Intermediate |
Official Website | Explore Free Course  |
Credential | Certificate |
Computer Vision with Embedded Machine Learning at Coursera Highlights
- Flexible deadlines Reset deadlines in accordance to your schedule.
- Shareable Certificate Earn a Certificate upon completion
- 100% online Start instantly and learn at your own schedule.
- Intermediate Level Some math (reading plots, arithmetic, and algebra) is required in the course. Experience with the Python is recommended to complete the projects.
Computer Vision with Embedded Machine Learning at Coursera Course details
- This course, offered by a partnership among Edge Impulse, OpenMV, Seeed Studio, and the TinyML Foundation, will give you an understanding of how deep learning with neural networks can be used to classify images and detect objects in images and videos. You will have the opportunity to deploy these machine learning models to embedded systems, which is known as embedded machine learning or TinyML.
- This course covers the concepts and vocabulary necessary to understand how convolutional neural networks (CNNs) operate, and it covers how to use them to classify images and detect objects. The hands-on projects will give you the opportunity to train your own CNNs and deploy them to a microcontroller and/or single board computer.
Computer Vision with Embedded Machine Learning at Coursera Curriculum
Image Classification
Welcome to the Course
Instructor Introductions
What is Computer Vision?
Overview of Digital Images
Data Collection
Overview of Image Classification
Review of Neural Networks
Training an Image Classifier with Keras
Using Colab to Curate and Upload a Dataset
Using Edge Impulse to Train a Model
Inference on a Single Board Computer
Inference on a Microcontroller (MicroPython)
Review of Module 1
Syllabus
Required Hardware
Getting Help
Slides
Slides
Python and Numpy Help
Project - Load and Manipulate Images
Slides
Image Classification and Neural Networks
Python and Edge Impulse Documentation
Project - Extract Features and Train Model
Edge Impulse and OpenMV Documentation
Project - Deploy DNN Image Classifier
Slides
Computer Vision
Image Classification with Neural Networks
Image Classification on Embedded Devices
Module 1 Review
Convolutional Neural Networks
Image Convolution
Pooling Layer
Convolutional Neural Network
Training a Convolutional Neural Network
CNN Visualizations
Data Augmentation
Transfer Learning and MobileNet
Transfer Learning with Edge Impulse
Review of Module 2
Slides
Project - Convolution and Pooling
Digging Deeper into CNNs
Slides
Project - Training a CNN
Slides
CNN Visualizations and Data Augmentation
Project - Data Augmentation
Digging Deeper into Transfer Learning
Slides
Project - Transfer Learning
Project - Deploy CNN Image Classifier
Slides
Convolution and Pooling
Convolutional Neural Networks
Visualizations and Data Augmentation
Transfer Learning
Module 2 Review
Object Detection
Introduction to Object Detection
Object Detection Performance Metrics
Object Detection Models
Training an Object Detection Model
Deploy Object Detection Model to a Single Board Computer
Image Segmentation
Multi-stage Inference with Dmitry Maslov
Reusing Representations with Mat Kelcey
Review of Module 3
Conclusion
Slides
Drawing API
Project - Sliding Window Object Detection
Slides
Digging Deeper into Object Detection
Deploying an Object Detection Model
Slides
Digging Deeper into Advanced Topics
Project - Deploy Object Detection Model
Slides
Object Detection
Image Segmentation
Module 3 Review
Computer Vision with Embedded Machine Learning at Coursera Admission Process
Important Dates
Other courses offered by Coursera
Student Forum
Anything you would want to ask experts?
Data ScienceMachine LearningMachine Learning and Pattern RecognitionComputer Vision with Embedded Machine Learning