AI & Automation · Self-paced course
Computer Vision & Deep Learning
Build and deploy deep learning models for image classification, object detection, and visual AI applications using PyTorch and TensorFlow.
$97
One-time payment · Self-paced course · 6 modules · 18 lessons
Enroll now — $97Read a free preview lesson
What this is
Build and deploy deep learning models for image classification, object detection, and visual AI applications using PyTorch and TensorFlow. The course covers: Convolutional neural networks (CNNs) from scratch; Transfer learning with ResNet, EfficientNet, and Vision Transformers; Object detection: YOLO, Faster R-CNN, and DETR; Image segmentation with U-Net and Mask R-CNN; OpenCV for real-time video processing; Deploying vision models with ONNX and TensorRT.
It is a self-paced course of written lessons and exercises. It does not include live instruction, one-to-one coaching or individual feedback on your work, and it cannot promise any particular job, income, ranking, certification or business result — what you get out of it depends on your own situation and the practice you put in.
What you will be able to do
- Convolutional neural networks (CNNs) from scratch
- Transfer learning with ResNet, EfficientNet, and Vision Transformers
- Object detection: YOLO, Faster R-CNN, and DETR
- Image segmentation with U-Net and Mask R-CNN
- OpenCV for real-time video processing
- Deploying vision models with ONNX and TensorRT
The curriculum
Module 1
Convolutional neural networks (CNNs) from scratch
- Key concepts
- Worked example
- Practice exercise
Module 2
Transfer learning with ResNet, EfficientNet, and Vision Transformers
- Key concepts
- Worked example
- Practice exercise
Module 3
Object detection: YOLO, Faster R-CNN, and DETR
- Key concepts
- Worked example
- Practice exercise
Module 4
Image segmentation with U-Net and Mask R-CNN
- Key concepts
- Worked example
- Practice exercise
Module 5
OpenCV for real-time video processing
- Key concepts
- Worked example
- Practice exercise
Module 6
Deploying vision models with ONNX and TensorRT
- Key concepts
- Worked example
- Practice exercise

This is for you if…
- You prefer to learn at your own pace from written lessons and exercises
- You want a structured path through Computer Vision & Deep Learning rather than scattered articles
- You are willing to practise on your own work as you go
- You want a one-time purchase rather than a subscription
What you get
- 18 lessons across 6 modules
- A free preview lesson you can read before you buy
- Practical exercises to apply each module to your own work
- Self-paced access — work through it on your own schedule
- One-time payment, no subscription
Questions
Is a certificate, licence or credential awarded?
No. This course does not award any certification, licence, accreditation or professional credential. It is educational content for your own learning.
Is this live or self-paced?
Fully self-paced. You work through the lessons on your own schedule; there are no live sessions.
Can I read a lesson before buying?
Yes. The free preview lesson linked at the top of this page is a complete lesson from the course.
How do I get access after paying?
Checkout is a one-time payment. After purchase, course access details are sent to the email address you use at checkout.
Computer Vision & Deep Learning
$97
One-time payment · Self-paced course · 6 modules · 18 lessons
Enroll now — $97Educational content only. This course does not promise any income, earnings, revenue, job or business results; outcomes depend on your own situation and effort. No certification, licence or professional credential is awarded.