Building Deep Learning Models Using PyTorch from Pluralsight

PyTorch is an open source deep learning framework originally developed by the AI teams at Facebook. PyTorch offers high-level APIs which make it easy to build neural networks and great support for distributed training and prediction.

PyTorch is an open source, deep learning framework which is a popular alternative to TensorFlow and Apache MXNet. PyTorch APIs follow a Python-native approach which, along with dynamic graph execution, make it very intuitive to work with for Python developers and data scientists.

In this course, Building Deep Learning Models Using PyTorch, you will learn to work with PyTorch and all the libraries that it has to offer, from first principles - starting with Torch tensors, dynamic computation graphs, and the autograd library, to compute gradients.

You'll start off by understanding the basics of training a neural network, the forward and backward passes, and gradient computation. You will use these concepts to build simple neural networks to predict automobile prices, as well as who survived and who did not on the Titanic.

Next, you'll move on to image classification using convolutional neural networks; you'll study the role of convolutional and pooling layers and the basic structure of a CNN, you'll then build a CNN to classify images from the Cifar-10 dataset. You'll also see how you can leverage the power of transfer learning by using pre-trained models for image classification.

Finally, you'll get to work with recurrent neural networks for sequence data, seeing how the dynamic computation graph execution in PyTorch makes building RNNs very simple. You'll use RNNs with long memory cells to predict gender using baby names.

At the end of this course, you will be comfortable using PyTorch libraries and APIs to leverage pre-trained models that PyTorch offers and also to build your own custom model for your specific use case.

What's inside

Syllabus

Course Overview

Introduction to PyTorch

Building Simple Neural Networks

Building an Image Classification Model

Building a Text Classification Model

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Teaches PyTorch, which is a popular alternative to TensorFlow and Apache MXNet and is popular in industry

Examines PyTorch APIs which follow a Python-native approach and allows for dynamic graph execution, which is simple and intuitive for Python developers and data scientists

Teaches the basics of training a neural network, forward and backward passes, and gradient computation

Builds custom deep learning models using PyTorch APIs and leverage pre-trained ones for specific use cases

Begins with fundamental concepts and gradually introduces advanced topics, making it suitable for beginners entering the field of PyTorch

Covers vast areas of PyTorch including simple neural networks, image classification, and text classification

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Building Deep Learning Models Using PyTorch with these activities:

Review linear algebra and calculus

Show steps

Strengthen your mathematical foundation by reviewing linear algebra and calculus, which are crucial for understanding the underlying concepts of neural networks and deep learning.

Browse courses on Linear Algebra

Show steps

Review concepts such as vectors, matrices, and linear transformations.
Practice solving calculus problems involving derivatives and integrals.
Utilize online resources or textbooks to refresh your memory.

Join a PyTorch study group or online community

Show steps

Enhance your learning journey by connecting with other PyTorch enthusiasts, discussing concepts, sharing ideas, and supporting each other's progress.

Browse courses on PyTorch

Show steps

Search for PyTorch study groups or online communities.
Join a group that aligns with your learning goals and engage in regular discussions.
Collaborate on projects, ask questions, and provide support to fellow learners.

Compile a repository of helpful PyTorch resources

Show steps

Enhance your learning experience by compiling a collection of valuable PyTorch resources, including tutorials, documentation, and code snippets.

Browse courses on PyTorch

Show steps

Search for and gather tutorials, articles, and code examples related to PyTorch.
Organize the resources into a structured format, such as a notebook or online repository.
Share your compilation with other learners or contribute it to the PyTorch community.

Five other activities

Expand to see all activities and additional details

Show all eight activities

Explore PyTorch's documentation

Show steps

Familiarize yourself with PyTorch's extensive documentation to gain a deeper understanding of its architecture, functions, and capabilities.

Browse courses on PyTorch

Show steps

Visit the official PyTorch website and explore the documentation.
Read through the tutorials and examples to understand PyTorch's basic concepts.
Experiment with the interactive tutorials and code snippets to gain hands-on experience.

Implement PyTorch models from scratch

Show steps

Enhance your understanding of PyTorch's inner workings by implementing different neural network models from scratch, gaining insights into their architecture and functionality.

Browse courses on PyTorch

Show steps

Choose a simple neural network architecture, such as a feedforward network or a convolutional neural network.
Implement the model in PyTorch, defining the layers, loss function, and optimizer.
Train and evaluate the model using a small dataset, observing its performance and making adjustments as needed.

Attend a PyTorch workshop or hackathon

Show steps

Accelerate your learning by participating in a PyTorch workshop or hackathon, where you can engage with experienced practitioners, work on projects, and expand your knowledge.

Browse courses on PyTorch

Show steps

Research and identify PyTorch workshops or hackathons in your area.
Register for the event and prepare to actively participate.
Engage with other participants, ask questions, and share your insights.

Build a custom image classification model using PyTorch

Show steps

Demonstrate your mastery of PyTorch by building a custom image classification model, applying your knowledge of neural networks to solve a real-world problem.

Browse courses on PyTorch

Show steps

Collect a dataset of images for your chosen classification task.
Design and implement a convolutional neural network architecture in PyTorch.
Train and evaluate your model, optimizing its performance on the dataset.

Contribute to the PyTorch community

Show steps

Deepen your understanding of PyTorch and make valuable contributions to the community by participating in open-source projects related to PyTorch.

Browse courses on PyTorch

Show steps

Identify open-source projects related to PyTorch on platforms like GitHub.
Choose a project that aligns with your interests and skills.
Read the project documentation and contribute bug fixes, feature enhancements, or new documentation.

Career center

Learners who complete Building Deep Learning Models Using PyTorch will develop knowledge and skills that may be useful to these careers:

Deep Learning Engineer

Deep Learning Engineers specialize in the development and application of deep learning models for a variety of tasks, such as image recognition, natural language processing, and speech recognition. They work closely with machine learning engineers and data scientists to design, build, and deploy deep learning models. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in building and deploying models using PyTorch.

See salaries and explore the career path for Deep Learning Engineer

Machine Learning Engineer

Machine Learning Engineers design, build, and deploy machine learning models to solve real-world problems. They work closely with data scientists to gather and prepare data, and with software engineers to integrate models into production systems. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in building and deploying models using PyTorch.

See salaries and explore the career path for Machine Learning Engineer

Data Scientist

Data Scientists use their skills in mathematics and statistics to solve complex problems using large amounts of data. They are employed across a wide range of industries and disciplines, from finance to manufacturing to healthcare. Building Deep Learning Models Using PyTorch can help prepare learners for this role by providing a strong foundation in the fundamentals of deep learning, including neural networks, gradient computation, and model evaluation.

See salaries and explore the career path for Data Scientist

Software Engineer

Software Engineers design, build, and maintain software systems. They work on a variety of projects, from small personal apps to large-scale enterprise systems. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in building and deploying models using PyTorch. This experience can be particularly valuable for Software Engineers who are working on projects that involve machine learning or artificial intelligence.

See salaries and explore the career path for Software Engineer

Data Analyst

Data Analysts use their skills in mathematics and statistics to analyze data and communicate insights to stakeholders. They work in a variety of industries, from finance to manufacturing to healthcare. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to analyze data and communicate insights.

See salaries and explore the career path for Data Analyst

Business Analyst

Business Analysts use their skills in business and data analysis to help organizations improve their performance. They work on a variety of projects, from process improvement to product development to financial analysis. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to analyze data and communicate insights. This experience can be particularly valuable for Business Analysts who are working on projects that involve machine learning or artificial intelligence.

See salaries and explore the career path for Business Analyst

Quantitative Analyst

Quantitative Analysts use their skills in mathematics, statistics, and programming to develop and apply mathematical models to financial data. They work on a variety of projects, from risk management to portfolio optimization to trading strategies. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to develop and apply mathematical models to data.

See salaries and explore the career path for Quantitative Analyst

Product Manager

Product Managers are responsible for the development and launch of new products. They work closely with engineers, designers, and marketers to ensure that products meet the needs of customers. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to develop and deploy models. This experience can be particularly valuable for Product Managers who are working on products that involve machine learning or artificial intelligence.

See salaries and explore the career path for Product Manager

Project Manager

Project Managers are responsible for planning, executing, and closing projects. They work on a variety of projects, from small personal projects to large-scale enterprise projects. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to develop and deploy models. This experience can be particularly valuable for Project Managers who are working on projects that involve machine learning or artificial intelligence.

See salaries and explore the career path for Project Manager

Consultant

Consultants provide advice and guidance to organizations on a variety of topics, including business strategy, operations, and technology. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to develop and deploy models. This experience can be particularly valuable for Consultants who are working with clients on projects that involve machine learning or artificial intelligence.

See salaries and explore the career path for Consultant

Researcher

Researchers conduct original research in a variety of fields, including science, engineering, and medicine. They work in a variety of settings, from academia to industry to government. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to develop and deploy models. This experience can be particularly valuable for Researchers who are working on projects that involve machine learning or artificial intelligence.

See salaries and explore the career path for Researcher

Teacher

Teachers educate students in a variety of subjects, from math to science to history. They work at all levels of education, from preschool to college. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to develop and deploy models. This experience can be particularly valuable for Teachers who are teaching courses on machine learning or artificial intelligence.

See salaries and explore the career path for Teacher

Writer

Writers create written content for a variety of audiences and purposes, including news articles, blog posts, marketing materials, and fiction. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to develop and deploy models. This experience can be particularly valuable for Writers who are writing about machine learning or artificial intelligence.

See salaries and explore the career path for Writer

Marketer

Marketers develop and execute marketing campaigns to promote products and services. They work in a variety of industries, from consumer goods to technology to healthcare. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to develop and deploy models. This experience can be particularly valuable for Marketers who are working on campaigns that involve machine learning or artificial intelligence.

See salaries and explore the career path for Marketer

Salesperson

Salespeople sell products and services to customers. They work in a variety of industries, from consumer goods to technology to healthcare. Building Deep Learning Models Using PyTorch can help learners prepare for this role by providing a strong foundation in the fundamentals of deep learning, as well as experience in using PyTorch to develop and deploy models. This experience can be particularly valuable for Salespeople who are selling products or services that involve machine learning or artificial intelligence.

See salaries and explore the career path for Salesperson