PyTorch is a Python-based open-source scientific computing library developed by Facebook that facilitates deep learning implementations. It was designed to provide similar production optimizations to TensorFlow while making it easier for users to create models. PyTorch is known to be flexible and high-speed, making it an excellent choice to build neural network models and deep learning architectures effortlessly. PyTorch accelerates the path from research prototyping to production deployment. Leading tech companies like Facebook, Twitter, NVIDIA, Uber, and others have used PyTorch extensively in many research fields such as natural language processing, machine translation, image recognition, etc.
TechClass Pytorch online course is developed as a practical approach to machine learning and deep learning using the PyTorch library. This course helps you gain hands-on experience building your predictive models, state-of-the-art image classifiers, and deep neural networks. By the end of this course, you will gain hands-on experience in designing, training, and evaluating variations of neural networks and learn the techniques required for working with large real-world datasets.
- Get familiar with PyTorch library and its capabilities
- Learn how to set up and get started with PyTorch in the Google Colab environment and your local system
- Learn about PyTorch’s Tensor data structure and how to work with them
- Gain hands-on experience building and training neural network models with PyTorch
- Gain hands-on experience evaluating neural networks and making predictions using them
- Learn how to use the nn module and its submodules
- Learn how to implement techniques to prevent overfitting in neural networks
- Get familiar with convolutional neural networks (CNNs), different layers of CNN, and popular CNN architectures
- Gain hands-on experience implementing CNN in PyTorch for computer vision tasks
- Learn how to analyze the performance of CNN after training
- Learn how to save and load the model’s parameters
- Learn about transfer learning and gain hands-on experience with VGG16 model
Table of contents
Chapter 1: Intro to Course
- 1.1. Welcome!
- 1.2. About TechClass Data Science Department
- 1.3. Learning Outcomes
- 1.4. Your Expectations, Goals, and Knowledge
- 1.5. Abbreviations
- 1.6. Copyright Notice
Chapter 2: Introduction
- 2.1. Machine Learning Pipeline: Part I
- 2.2. Machine Learning Pipeline: Part II
- 2.3. How do deep learning algorithms work?
- 2.4. Top Deep Learning Algorithms
- 2.5. Deep Learning Frameworks
- 2.6. What Is PyTorch?
- 2.7. Setting up PyTorch in Your Local System
- 2.8. Getting Started with Google Colab
Chapter 3: Python Overview
- 3.1. Variables and Operations
- 3.2. Data Structures
- 3.3. Conditional Statements
- 3.4. Loops
- 3.5. A Review on NumPy Library
- 3.6. NumPy Arrays
- 3.7. NumPy Array Math
- 3.8. NumPy Array Indexing
- 3.9. Classes
- 3.10. Exercise
- 3.11. Quiz
Chapter 4: Tensors in PyTorch
- 4.1. Tensor: Getting Started
- 4.2. Tensors and PyTorch
- 4.3. Initializing Tensors
- 4.4. Tensors with Special Values
- 4.5. Attributes of Tensors
- 4.6. Tensors Indexing and Slicing
- 4.7. Operations on Tensors
- 4.8. Quiz
Chapter 5: Build Your First Model in PyTorch
- 5.1. Machine Learning Models in General
- 5.2. Linear Regression and Neuron
- 5.3. A Review on Cost Functions and MSE
- 5.4. Gradient Descent Algorithm
- 5.5. Linear Regression: NumPy Implementation
- 5.6. Linear Regression: PyTorch Implementation
- 5.7. NumPy Array and PyTorch Tensor Bridge
- 5.8. Defining Models in PyTorch: Sequential and Module
- 5.9. Loss Function in PyTorch
- 5.10. Gradients in PyTorch
- 5.11. Optimization in PyTorch
- 5.12. Exercise
Chapter 6: Creating Feed-Forward Neural Networks
- 6.1. Review on Feed Forward Neural Networks
- 6.2. Creating Model Using nn Module
- 6.3. Creating Custom Datasets Using Dataloaders Module
- 6.4. Training the Model
- 6.5. Prediction and Evaluation
Chapter 7: Convolutional Neural Networks
- 7.1. Why CNN?
- 7.2. CNN Layers: Part I
- 7.3. CNN Layers: Part II
- 7.4. Typical CNN Architecture
- 7.5. Implementing CNN In PyTorch
- 7.6. Popular CNN Architectures for Computer Vision
- 7.7. Loading and Preprocessing CIFAR10 Dataset
- 7.8. Training and Evaluating CNN for CIFAR10 Dataset
Chapter 8: Saving and Loading Models
- 8.1. Introduction
- 8.2. Saving and Loading Model Weights
- 8.3. Saving and Loading Models with Shapes
- 8.4. Exporting Model to ONNX
Chapter 9: Transfer Learning
- 9.1. What is Transfer Learning?
- 9.2. How to Use Transfer Learning?
- 9.3. Loading Pre-trained Models
- 9.4. Pre-trained Models as Classifiers
- 9.5. Pre-trained Model as Standalone Feature Extractor
- 9.6. Pre-trained Model as Integrated Feature Extractor
Chapter 10: Final Tasks
- 10.1. Final Project
- 10.2. Self-study Essay
Chapter 11: Finishing the Course
- 11.1. What We Have Learned
- 11.2. Where to Go Next?
- 11.3. Your Opinion Matters
- 11.4. Congrats! You did it!
Payment & Security
Your payment information is processed securely. We do not store credit card details nor have access to your credit card information.
This course simplified the concepts that made me I could easily understand.
It starts from basic concepts and some refreshing topics to modern PyTorch examples.
Perfect foundational overview of the topic with challenging exercises. You will gian hands-on expericne with PyTorch.
- Opens in a new window.