CF

The Computer Vision Bootcamp

6h 8m 8s
English
Paid

The Computer Vision Bootcamp is a 49-lesson 6 hours 8 minutes self-paced course by Zero To Mastery. Computer Vision is one of the most rapidly developing fields of artificial intelligence , enabling systems to analyze images and videos as well as, and sometimes better than, humans.

Course facts

Lessons
49
Duration
6 hours 8 minutes
Level
All levels
Language
English
Updated
Instructor
Zero To Mastery
Price
Premium

Computer Vision is one of the most rapidly developing fields of artificial intelligence, enabling systems to analyze images and videos as well as, and sometimes better than, humans. This course will help you not only understand the basics of CV but also deeply study modern models and learn to apply them in production.

What is computer vision and why it is needed

Computer vision trains systems to "see" and interpret visual data: identifying objects, tracking movement, recognizing faces, highlighting areas in an image, and even reading text. It is the key technology behind:

  • autopilots and driverless cars;
  • medical diagnostics;
  • surveillance systems and facial recognition;
  • robotics and production automation;
  • tools for marking and analyzing visual data.

The main goal is to convert pixel data into structured information, making decisions based on visual context.

What you will learn at the bootcamp

During the course, you will explore modern computer vision architectures, including Vision Transformers and the SAM segmentation model from Meta, and learn to apply them in real projects.

Key skills and competencies

  • Deeply understand how Vision Transformers process images.
  • Analyze the structure and mathematics of the attention mechanism.
  • Use Meta SAM for segmentation based on textual requests.
  • Visualize results and assess segmentation quality.
  • Combine detection and segmentation models into unified pipelines.
  • Create scalable CV projects in Python.
  • Deploy computer vision models in AWS.
  • Design production-ready AI systems for real products.

Practical focus of the course

The course is focused on applying technologies: each lesson ends with a practical assignment, culminating in a complete CV project ready for deployment in production.

Industry tools and frameworks

  • PyTorch and TensorFlow;
  • Hugging Face Transformers;
  • OpenCV and torchvision;
  • toolkits for working with segmentation and detection;
  • AWS S3, Lambda, EC2 for model production.

Learning outcome

Upon completion of the bootcamp, you will not only understand how modern computer vision models are structured but also be able to independently build, optimize, and deploy complete CV systems in a cloud infrastructure.

Additional

https://github.com/patrikszepesi/META-SAM-course

Who teaches The Computer Vision Bootcamp? Zero To Mastery

Zero To Mastery thumbnail

Zero To Mastery (ZTM) is a Toronto-based online coding academy founded by Andrei Neagoie, originally a senior developer at large Canadian tech firms before turning to teaching full-time. The academy's signature is the cohort-based bootcamp track combined with a deep self-paced course library, all aimed at career-changers and self-taught developers preparing to land software-engineering roles at top companies.

The instructor roster has grown well beyond Andrei to include other senior practitioners: Daniel Bourke (machine learning), Aleksa Tešić (DevOps), Jacinto Wong, and others. Courses cover the full software-engineering career path: web development with React and Next.js, Python, machine learning and deep learning, DevOps and cloud, system design, mobile, and the algorithm / data-structure interview prep that gates engineering jobs.

The CourseFlix listing under this source carries over 120 ZTM courses spanning that full range. Material is paid; ZTM itself runs on a monthly / annual membership model. The teaching style favours long-form, project-based courses where students build complete portfolio-quality applications rather than disconnected feature tutorials.

What lessons are included in The Computer Vision Bootcamp?

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 49 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Introduction
All Course Lessons (49)
#Lesson TitleDurationAccess
1
Introduction Demo
05:31
2
What We're Building
04:33
3
Vision Transformers vs Convolutional Neural Networks
05:29
4
Quadratic Operations
09:43
5
Introduction to ViTs and Joint Training with Embeddings
10:49
6
Understanding Attention Mechanisms, Brief Summary
05:19
7
Understanding the Full ViT Pipeline
17:14
8
Introduction to Prompt Encoders for SAM
04:57
9
SAM AutoPrompt Mode
15:37
10
SAM Manual Click Mode
07:55
11
ViT Embeddings inside SAM
04:55
12
Calculating Attention Score for Vision Transformers in SAM
16:42
13
How SAM is Trained
08:05
14
Calculating Prompt Self Attention for SAM
04:08
15
Prompt Image Cross Attention
07:36
16
Image to Prompt Cross Attention
05:56
17
(Optional) Finishing SAM Example Part 1
08:50
18
(Optional) Finishing SAM Example Part 2
07:33
19
Creating our SagemakerAI Domain
01:00
20
Starting Domain and Understanding Pricing
03:15
21
Installing Libraries
03:50
22
Stopping Instances and Servers
00:38
23
Downloading the SAM Model from Meta
03:24
24
Updating IAM Permissions
01:56
25
Importing Libraries
05:01
26
Understanding how we use Rekognition with SAM
12:29
27
Defining Helper Functions
12:37
28
Clarification Regarding Helper Functions
01:36
29
Rekognition Detection and Filtering
12:27
30
Initialise SAM Model from S3
10:16
31
Main Processing Function Part 1
14:34
32
Main Processing Function Part 2
03:51
33
Running the Main Processing Cell
04:54
34
Visualizing Rekognition Detections
07:50
35
Visualize All SAM Masks
09:28
36
Visualizing Match Quality IOU Scores Part 1
10:23
37
Visualizing Match Quality IOU Scores Part 2
09:30
38
Visualizing Image Segmentations with Bounding Boxes
11:03
39
Visualizing Masks and Labels Without Bounding Boxes
06:31
40
Visualizing Segementations in Black and White Masks
04:38
41
Exercise: Imposter Syndrome
02:57
42
Saving Metadata to S3
09:07
43
Save Images to S3
10:12
44
Saving Individual Masks to S3
08:56
45
Adding a GPU Server to our Notebook and AWS Quotas
05:24
46
Testing Our Full Pipeline
08:22
47
Minor Corrections
13:10
48
Productionizing + Cleanup
06:39
49
Thank You!
01:18
Unlock unlimited learning

Get instant access to all 48 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

What courses are similar to The Computer Vision Bootcamp?

  • Machine Learning & Containers on AWS thumbnailUpdated 1y ago

    Machine Learning & Containers on AWS

    By: Andreas Kretz
    In this practical course, you will learn how to build a complete data pipeline on the AWS platform - from obtaining data from the Twitter API to analysis, stora
    1h 33m5/5
  • Codex - The Practical Guide thumbnailUpdated 1mo ago

    Codex - The Practical Guide

    By: Academind Pro (Maximilian Schwarzmüller)
    Study Codex from the basics to advanced techniques. The course will help you use it as an intelligent assistant, enhancing your skills and increasing productivi
    3h 10m
  • Build a DeepSeek Model (From Scratch) thumbnailUpdated 2mo ago

    Build a DeepSeek Model (From Scratch)

    By: Rajat Dandekar, Naman Dwivedi, Dr. Sreedath Pana
    Learn how to build a DeepSeek model from scratch. A practical guide with a focus on engineering and algorithmic solutions for efficient model performance.
  • Vibe Code a Generative AI Finance App with Python and LangChain thumbnailUpdated 2mo ago

    Vibe Code a Generative AI Finance App with Python and LangChain

    By: Zero To Mastery
    Master the creation of AI applications for investments using Python and LangChain. Practice developing a fintech application and understanding financial metrics
    7h 36m5/5
  • ML Project Blueprint thumbnailNew

    ML Project Blueprint

    By: Timur Bikmukhametov
    Learn how to create a complete ML solution from data to cloud deployment. Master the end-to-end pipeline and professional code architecture.
    2h 55m
  • Agentic AI Engineering Course thumbnailUpdated 2mo ago

    Agentic AI Engineering Course

    By: Paul Iusztin, Towards AI, Louis-François Bouchard
    Become an expert in creating AI agent systems for production. Learn how to develop scalable AI agents and make them work in real-world conditions.
    7h 33m5/5
  • Sutskever's List thumbnailNew

    Sutskever's List

    By: Richard Heimann
    Study 30 key scientific papers on artificial intelligence with Rich Heymann. Breakthrough ideas of Sutskever in the field of deep learning.

More courses by Zero To Mastery

Frequently asked questions

What are the prerequisites for enrolling in this course?
The course assumes a basic understanding of programming, specifically in Python, as it covers creating scalable computer vision projects using this language. Familiarity with cloud services like AWS would be beneficial as the course involves deploying models in AWS. A fundamental knowledge of neural networks and machine learning concepts will help in understanding advanced topics like Vision Transformers and the SAM segmentation model.
What kind of projects will I build during the course?
Throughout the course, you will work on creating scalable computer vision projects. You will integrate Vision Transformers and the SAM segmentation model from Meta into pipelines, and deploy these models on AWS. The course includes hands-on exercises such as visualizing segmentations, combining detection and segmentation models, and creating production-ready applications.
Who is the target audience for this course?
This course is designed for individuals who have an interest in artificial intelligence and want to specialize in computer vision. It is suitable for those who are looking to understand modern computer vision architectures and apply them in real-world scenarios, such as developers, data scientists, and AI researchers.
How does this course compare to other computer vision courses?
This course offers a detailed exploration of modern computer vision models, such as Vision Transformers and Meta's SAM segmentation model, with a focus on applying these in production. Unlike some basic courses, it provides insights into deploying models on AWS and creating scalable projects, making it suitable for those looking to implement computer vision solutions in professional settings.
What specific tools or platforms does the course cover?
The course covers various tools and platforms essential for computer vision projects. Key topics include Vision Transformers, SAM segmentation model from Meta, AWS for model deployment, and Python for building scalable CV projects. Students will also learn to use Amazon Rekognition and S3 for managing models and data.
What topics are not covered in this course?
The course does not cover basic computer vision concepts such as simple image processing techniques or traditional machine learning algorithms. It focuses on advanced models and their application, so foundational topics might need to be learned separately if not already familiar.
What is the expected time commitment for completing this course?
The course consists of 49 lessons, and while the total runtime is not specified, prospective students should allocate sufficient time for both the theoretical and practical components. Engaging with complex topics like Vision Transformers and model deployment on AWS, alongside exercises, will require a substantial time investment.