Computer Vision Generative AI using Deep Learning, Learn Generative AI architectures, Get started with Deep Learning
- Free tutorial
- Rating: 4.3 out of 54.3 (11 ratings)
- 561 students
- 1hr 14min of on-demand video
- Created by The3rd AI
- English
What you’ll learn
- Learn the core concepts and techniques used in computer vision, including image processing, feature extraction.
- Gain practical experience by implementing computer vision models using PyTorch
- Dive deep into CNNs, the backbone of modern computer vision, and explore architectures like VAE, UNet etc. to enhance your understanding of deep
- Understand how to leverage pretrained models to expedite the training process in computer vision tasks while working with limited data.
- Understand how Generative AI works implement them
Requirements
- You must know Python as a pre-requisite. In this course I am also covering the basics of Deep Learning, it would be good if you are aware of basic data science concepts, but it’s not a necessity..
Description
In this course, you will embark on a journey to master the foundations of deep learning and apply them to various computer vision tasks. Whether you’re a beginner or an experienced practitioner, this course will equip you with the knowledge and practical skills needed to excel in the field.
This course only focuses on the things which are required to get you started in coding Neural Networks for computer vision tasks. This course is focused on clearing your Deep Learning and Computer Vision Concepts, that’s why I have kept it short and Free. From the next course, you would see much longer courses focused towards teaching you Advanced Computer Vision.
Each section starts with theory, gives you an idea about how things work, and then gives you hands-on examples through coding videos.
You’ll dive into “Deep Learning Fundamentals” to establish a solid understanding of the principles that drive this cutting-edge field. You’ll explore topics such as neural networks, Tensors, PyTorch etc.
In “Building Neural Networks with PyTorch,” you’ll learn how to construct powerful neural networks using the PyTorch library. Through hands-on coding exercises, you’ll gain the skills to design, train, and evaluate neural networks for a variety of tasks.
The “Neural Network for Images” section focuses on leveraging neural networks for image classification, object detection, and semantic segmentation. You’ll learn how to preprocess image data, build custom architectures, and apply transfer learning to achieve state-of-the-art performance.
“Convolutional Neural Networks” takes a deep dive into this key architecture for computer vision. You’ll understand the unique characteristics of CNNs, learn how to fine-tune them for specific tasks.
The “Autoencoders” section introduces unsupervised learning and dimensionality reduction techniques using autoencoders. You’ll delve into various types of autoencoders, including convolutional and variational autoencoders, and apply them to projects involving image reconstruction and generation.
Finally, the “Projects” section will put your skills to the test as you tackle exciting real-world applications. You’ll explore projects like “Deep Fake” where you’ll generate realistic face swaps, “Image Colorization” to bring black and white images to life, and “Neural Style Transfer” to create artistic transformations.
By the end of this course, you’ll have gained a comprehensive understanding of deep learning and computer vision with PyTorch. You’ll be proficient in building and training neural networks, applying convolutional networks to image analysis, and utilizing generative models for creative projects. Join us now and unlock the potential of deep learning in the realm of computer vision!
Who this course is for:
- Data scientists curious about computer vision and Generative AI
- AI Enthusiasts who want to learn about computer vision and generative AI
Show less
Course content
7 sections • 41 lectures • 1h 14m total lengthCollapse all sections
Introduction2 lectures • 5min
- Introduction01:29
- Course Overview03:15
Deep Learning Fundamentals7 lectures • 11min
- What is Deep Learning01:35
- Introduction to PyTorch01:12
- Tensor01:17
- Tensor (Coding)02:03
- Operations on tensor (Coding)01:29
- Operations on tensor part 2(Coding)01:47
- Advantages of tensors01:22
Building Neural Networks with PyTorch11 lectures • 20min
- What is a Neural Network01:44
- Neural Network Training Workflow02:18
- Neural Network Architecture01:48
- Architecture (Coding)01:00
- Activation and Loss Functions02:20
- Activation and Loss Functions (Coding)01:41
- Optimizers01:44
- Training Neural Network (Coding)01:13
- Dataset and Data Loader01:55
- Dataset and Data Loader (Coding)01:32
- Sequential02:46
Neural Network for Images6 lectures • 10min
- Introduction to Image Classification01:58
- Fundamentals of Image Processing (Coding)01:03
- Image Classification (Coding)01:35
- Hyperparameter Tuning01:52
- Deep Neural Network (Coding)02:03
- Data Normalization01:33
Convolutional Neural Networks (CNNs)6 lectures • 10min
- Introduction to CNN01:46
- Why CNN?01:31
- CNN (Coding)01:49
- Data Augmentation00:56
- Training with Augmented Data (Coding)02:24
- CNN on Real World Images01:43
Auto Encoders5 lectures • 9min
- Introduction to Auto Encoders01:33
- Vanilla Auto Encoders (Coding)01:28
- CNN Based Auto Encoder (Coding)02:57
- Introduction to Variational Auto Encoders (VAE)01:17
- VAE (Coding)01:56
Hands-on Projects4 lectures • 9min
- Section Overview01:54
- Neural Style Transfer (Coding)03:28
- Deep Fake (Coding)01:49
- Image Colorization (Coding)02:04
