Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Modern Computer Vision & Deep Learning with Python & PyTorch

Name: Modern Computer Vision & Deep Learning with Python & PyTorch
Rating: 4.3 (350 reviews)

Computer Vision with Python using Deep Learning for Classification, Instance and Semantic Segmentation, Object Detection

Created byMazhar Hussain, AI & Computer Science School

Last updated 6/2026

English

English [Auto],

What you'll learn

Learn Computer Vision and Deep Learning with Real-world Applications in Python
Computer Vision for Single and Multi-label Classification with Python and Pytorch
Computer Vision for Image Semantic Segmentation with Python and Pytorch
Computer Vision for Image Instance Segmentation with Python and Pytorch
Computer Vision for Object Detection & Tracking with Python and Pytorch
Learn Deep Convolutional Neural Networks (CNN) for Computer Vision
Google Colab with GPU for Writing Python and Pytorch Code
Learn Data Augmentation with Different Image Transformations
Custom Datasets for Image Classification, Image Segmentation, Object Detection & Tracking
Hyperparameters Optimization of Deep Learning Models to Improve Performance
Learn Performance Metrics (Accuracy, IOU, Precision, Recall, Fscore)
Transfer Learning with Pretrained Models of Deep Learning in Pytorch
Train Image Segmentation, Classification and Object Detection Models on Custom Datasets
Evaluate and Deploy Image Segmentation, Image Classification and Object Detection Models
Object Detection using Detectron2 Models Introduced by Facebook Artificial Intelligence Research (FAIR) Group
Perform Object Detection using YOLO8, YOLO11, YOLO26, RCNN, Fast RCNN, Faster RCNN Models with Python and Pytorch
Perform Semantic Segmentation with YOLO26, UNet, PSPNet, DeepLab, PAN, and UNet++ Models with Pytoch and Python
Perform Instance Segmentation using YOLO26, Mask RCNN on Custom Dataset with Pytorch and Python
Perform Image Single and Multi-label Classification using Deep Learning Models (ResNet, AlexNet) with Pytorch and Python
Visualization of Results, Datasets, and Complete Python/Pytorch Code is Provided for Classification, Segmentation, and Object Detection

Course content

32 sections • 108 lectures • 12h 5m total length

Introduction to Computer Vision Course3:20
Explore how computer vision enables machines to see and interpret the visual world with deep learning, Python, and PyTorch, building models for image classification, semantic segmentation, and object detection.

Introduction to Computer Vision and its Real-world Applications11:08
Explore how computer vision enables machines to see images and videos, extract meaning, and perform tasks like object detection, image classification, and scene understanding for real-world applications.
Major Computer Vision Tasks2:40
Explore major computer vision tasks, including image classification, object detection with bounding boxes, semantic segmentation with pixel-level labeling, and instance segmentation that differentiates object instances.

Computer Vision using Convolutional Neural Networks (CNN)9:15
Explore how convolutional neural networks power computer vision tasks—from image classification to object detection and segmentation—through layers, pooling, activation functions, and notable architectures like LeNet, AlexNet, GoogLeNet, VGG, and ResNet.
Setting-up Google Colab for Writing Python Code7:24
Learn how to set up and use Google Colab for writing Python code, access GPUs and TPUs, and connect Colab to Google Drive for storing and sharing notebooks.
Coding Convolutional Neural Network Architecture from Scratch27:16
Build a convolutional neural network from scratch in PyTorch, featuring two conv layers, ReLU, two max pooling layers, and three fully connected layers, trained on CIFAR-10 with data augmentation.
Convolutional Neural Networks HyperParameters Optimization10:01
Explore how hyperparameters optimize deep learning models by minimizing loss with optimizers like Adam, including learning rate, decay, and loss definition for CIFAR ten image classification.
Training Convolutional Neural Network from Scratch4:03
Train a custom convolutional neural network on CIFAR ten dataset for image classification over ten epochs, using data loaders, forward and backward passes, and tracking training loss and accuracy.
Calculate Accuracy, Precision, Recall and Visualize Confusion Matrix15:16
Learn how to evaluate classification models using accuracy, precision, recall, and F1 score, interpret confusion matrices, and visualize the results with Seaborn and Plotly.
Resources: Complete Code for CNN from Scratch with Python and Pytorch0:04

Image Classification Task of Computer Vision with Pytoch and Python2:59
Explore image classification, a computer vision task that predicts a single label or multiple labels for an input image, distinguishing single label from multi-label classification.
Image Classification with Deep Convolutional Neural Networks using Python23:18
Deepen a conv net to four convolutional layers with two pooling layers and two fully connected layers, defining per-layer parameters, trained on cifar-10 with learning rate decay for higher accuracy.
Resources: Code for Image Classification with Deep CNN from Scratch0:05

Introduction to Pretrained Models5:11
Explore single label and multi-label classification with pretrained models in PyTorch, learn transfer learning using weights from ResNet and AlexNet trained on ImageNet, and apply to new datasets.
Deep Learning ResNet and AlexNet Architectures4:58
Compare deep learning architectures for image classification, focusing on ResNet and AlexNet, their layers, convolutional blocks, pooling, and the use of pre-trained networks on ImageNet.
Access Data from Google Drive to Colab2:44
Learn to access data from Google Drive in Colab by uploading images to a data folder, reading them with Python using PIL, and displaying them with Pyplot.
Data Preprocessing for Image Classification5:00
Preprocess the input image for prediction by resizing to 256, center-cropping to 224, converting to a tensor, and normalizing with mean and standard deviation, then batch for resnet or alexnet.
Single-Label Image Classification using ResNet and AlexNet PreTrained Models8:03
Perform single-label image classification with pre-trained Resnet 101 and AlexNet models from torchvision on ImageNet 1000 classes, mapping predicted IDs to class names and comparing performance with a pizza example.
Single Label Classification Python and Pytorch Code0:03
Multi-Label Image Classification using Deep Learning Models6:21
Learn to perform multi-label image classification using deep learning models such as ResNet and AlexNet in Colab, applying sigmoid activation to predict multiple labels and output the top five predictions.
Multi-Label Classification Python and PyTorch Code0:03

Introduction to Transfer Learning6:09
Discover how transfer learning reuses pre-trained models to solve new tasks, boosting generalization and reducing training time. Compare fine-tuning with fixed feature extraction to apply knowledge across tasks.
Dataset, Data Augmentation, and Dataloaders7:20
Explore a three-class image dataset (bread, coffee, pasta) and apply data augmentation, with random resize crop and horizontal flip, while implementing data loaders for training and validation.
Dataset for Classification0:02
FineTuning Deep ResNet Model7:19
Fine-tune a pretrained ResNet-101 in Torch Vision on Google CoLab by replacing the final fully connected layer. Compare this with using the pretrained model as a fixed feature extractor.
HyperParameteres Optimization for Model6:22
Explore model optimization by tuning hyperparameters to minimize loss in deep learning, using optimizers like Adam, learning rate decay, and loss functions such as cross-entropy in PyTorch.
Training Deep ResNet Model3:34
Train a resnet fine tuning model using a loss function, optimizer, and learning-rate decay for 20 epochs, saving to Google Drive, then load and visualize results with validation accuracy insights.
Fixed Feature Extractraction using ResNet4:42
Perform transfer learning with a pre-trained ResNet as a fixed feature extractor by freezing all layers except the final fully connected layer, replacing it, and training only that layer.
Model Optimization, Training and Results Visualization5:51
Compare Resnet feature extractor optimization with fine tuning using transfer learning: optimize only the final layer vs all parameters, train 20 epochs, and visualize results showing 56% vs 100% accuracy.
Complete Python Code for Transfer Learning and Dataset0:02

Overview of YOLO Family38:00
Trace the YOLO family evolution from the original to YOLO seven, highlighting real-time object detection, anchor boxes, grid cells, and architecture advances that boost speed and accuracy.
YOLO Family Research Papers0:02
YOLOv8 and its Architecture13:36
Explore YOLOv8 by Ultralytics, a state-of-the-art, anchor-free vision framework offering detection, segmentation, pose estimation, tracking, and classification powered by the C2F backbone and decoupled head.

Requirements

Computer Vision and Deep Learning with Python and Pytorch is taught in this course by following a complete pipeline from Zero to Mastery
No prior knowledge of Computer Vision and Deep Learning is assumed. Everything will be covered with hands-on trainings
A Google Gmail account is required to get started with Google Colab to write Python and PytorchCode

Description

Welcome to the course "Modern Computer Vision & Deep Learning with Python & PyTorch"! Imagine being able to teach computers to see just like humans. Computer Vision is a type of artificial intelligence (AI) that enables computers and machines to see the visual world, just like the way humans see and understand their environment. Artificial intelligence (AI) enables computers to think, where Computer Vision enables computers to see, observe and interpret. This course is particularly designed to provide a comprehensive, hands-on experience in applying Deep Learning techniques to major Computer Vision problems including Image Classification, Semantic Segmentation, Instance Segmentation, and Object Detection. In this course, you'll start with an introduction to the basics of Computer Vision and Deep Learning, and learn how to implement, train, test, evaluate and deploy your own models using Python and PyTorch for Image Classification, Image Segmentation, and Object Detection.

Computer Vision plays a vital role in the development of autonomous vehicles. It enables the vehicle to perceive and understand its surroundings to detect and classify various objects in the environment, such as pedestrians, vehicles, traffic signs, and obstacles. This helps to make informed decisions for safe and efficient vehicle navigation. Computer Vision is used for Surveillance and Security using drones to track suspicious activities, intruders, and objects of interest. It enables real-time monitoring and threat detection in public spaces, airports, banks, and other security-sensitive areas. Today Computer Vision applications in our daily life are very common including Face Detection in cameras and cell phones, logging in to devices with fingerprints and face recognition, interactive games, MRI, CT scans, image guided surgery and much more. This comprehensive course is especially designed to give you hands-on experience using Python and Pytorch coding to build, train, test and deploy your own models for major Computer Vision problems including Image Classification, Image Segmentation (Semantic Segmentation and Instance Segmentation), and Object Detection. So, are you ready to unleash the power of Computer Vision and Deep Learning with Python and PyTorch:

Master the cutting-edge techniques and algorithms driving the field of Computer Vision.
Dive deep into the world of Deep Learning and gain hands-on experience with Python and PyTorch, the industry-leading framework.
Discover the secrets behind building intelligent systems that can understand, interpret, and make decisions from visual data.
Unlock the power to revolutionize industries such as healthcare, autonomous systems, robotics, and more.
Gain practical skills through immersive projects, real-world applications, and hands-on coding exercises.
Gain insights into best practices, industry trends, and future directions in computer vision and deep learning.

What You'll Learn:

This course covers the complete pipeline with hands-on experience of Computer Vision tasks using Deep Learning with Python and PyTorch as follows:

Introduction to Computer Vision and Deep Learning with real-world applications
Learn Deep Convolutional Neural Networks (CNN) for Computer Vision
You will use Google Colab Notebooks for writing the python and Pytorch code.
Perform two types of Image Classification using Deep Learning models with Python.
- Single-label Classification.
- Multi-label Classification.
You will be able to learn Transfer Learning techniques:
- Transfer Learning by FineTuning the Model.
- Transfer Learning by using the Model as Fixed Feature Extractor.
You will learn how to perform Data Augmentation.
You will Learn to FineTune the Deep Resnet Model.
You will learn how to use the Deep Resnet Model as Fixed Feature Extractor.
You will Learn HyperParameters Optimization and results visualization.
Semantic Image Segmentation and its Real-World Applications in Self Driving Cars or Autonomous Vehicles etc.
Deep Learning Architectures for Semantic Segmentation including:
- UNet, and UNet++
- Pyramid Scene Parsing Network (PSPNet),
- Pyramid Attention Network (PAN),
- Multi-Task Contextual Network (MTCNet),
- DeepLabV3, etc.
- YOLO26
Datasets and Data annotations Tool for Semantic Segmentation
Data Augmentation and Data Loading in PyTorch for Semantic Segmentation
Performance Metrics (IOU) for Segmentation Models Evaluation
Segmentation Models Implementation in PyTorch using different Encoder and Decoder Architectures
Hyperparameters Optimization and Training of Segmentation Models
Test Segmentation Model and Calculate IOU, Class-wise IOU, Pixel Accuracy, Precision, Recall and F-score
Visualize Segmentation Results and Generate RGB Predicted Segmentation Map
Learn Object Detection using Deep Learning Models with Pytorch
Learn Object Detection Deep Learning Architecture:
- YOLO8
- YOLO11
- YOLO26
- RCNN,
- Fast RCNN,
- Faster RCNN
- Mask RCNN
Perform Object Detection with Fast RCNN and Faster RCNN
Introduction to Detectron2 by Facebook AI Research (FAIR)
Preform Object Detection with Detectron2 Models
Explore Custom Object Detection Dataset with Annotations
Perform Object Detection on Custom Dataset using Deep Learning
Train, Test, Evaluate Your Own Object Detection Models and Visualize Results
Perform Instance Segmentation using Mask RCNN on Custom Dataset with Pytorch and Python

Who Should Attend:

This course is designed for a wide range of students and professionals, including but not limited to:

Computer Vision Engineers, Artificial Intelligence AI enthusiasts and Researchers who want to learn how to use Python adn PyTorch to build, train and deploy Deep Learning models for Computer Vision problems
Machine Learning Engineers, Deep Learning Engineers, and Data Scientists who want to apply Deep Learning to Computer Vision tasks
Developers who want to incorporate Computer Vision and Deep Learning capabilities into their projects
Graduates and Researchers in Computer Science, Electrical Engineering, and other related fields who want to learn about the latest advances in Deep Learning for Computer Vision
In general, the course is for Anyone who wants to learn how to use Deep Learning to extract meaning from visual data and gain a deeper understanding of the theory and practical applications of Computer Vision using Python and PyTorch

This course is designed for AI enthusiasts, data scientists, software engineers, researchers, and anyone passionate about unlocking the potential of computer vision and deep learning. Whether you're a seasoned professional or just starting your journey, this course will equip you with the skills and knowledge needed to excel in this rapidly evolving field.

Join the Visionary Revolution:

Don't miss out on this incredible opportunity to join the visionary revolution in modern Computer Vision & Deep Learning. Expand your skill set, push the boundaries of innovation, and embark on a transformative journey that will open doors to limitless possibilities. By the end of this course, you'll have the knowledge and skills you need to start applying Deep Learning to Computer Vision problems including Image Classification, Image Segmentation, and Object Detection in your own work or research. Whether you're a Computer Vision Engineer, or Developer, this course is the perfect way to take your understanding of Deep Learning to the next level. Let's get started on this exciting journey of Deep Learning for Computer Vision with Python and PyTorch.

See you inside the Class!!

Who this course is for:

This course is designed for individuals who are interested in learning how to apply Deep Learning techniques to solve Computer Vision problems in real-world using the Python programming language and the PyTorch Deep Learning Framework
Computer Vision Engineers, Artificial Intelligence AI enthusiasts and Researchers who want to learn how to use Python adn PyTorch to build, train and deploy Deep Learning models for Computer Vision problems
Machine Learning Engineers, Deep Learning Engineers, and Data Scientists who want to apply Deep Learning to Computer Vision tasks
Developers, Graduates and Researchers who want to incorporate Computer Vision and Deep Learning capabilities into their projects
In general, the course is for Anyone who wants to learn how to use Deep Learning to extract meaning from visual data and gain a deeper understanding of the theory and practical applications of Computer Vision using Python and PyTorch

Modern Computer Vision & Deep Learning with Python & PyTorch

What you'll learn

Explore related topics

Course content

Introduction to Course1 lecture • 3min

What is Computer Vision & its Applications2 lectures • 14min

Deep Learning for Computer Vision1 lecture • 23min

Computer Vision and Deep Convolutional Neural Networks7 lectures • 1hr 13min

1. Image Classification Task of Computer Vision3 lectures • 26min

Pretrained Models for Single and Multi-Label Image Classification8 lectures • 32min

Transfer Learning for Image Classification9 lectures • 41min

Annotation tools to Label Your Own Datasets for Computer Vision1 lecture • 2min

2. Object Detection Task Of Computer Vision1 lecture • 8min

Overview of YOLO Family for Object Detection3 lectures • 52min

Requirements

Description

Who this course is for: