Let us help you find the training program you are looking for.

If you can't find what you are looking for, contact us, we'll help you find it. We have over 800 training programs to choose from.

Deep Learning with PyTorch

  • Course Code: Artificial Intelligence - Deep Learning with PyTorch
  • Course Dates: Contact us to schedule.
  • Course Category: AI / Machine Learning Duration: 4 Days Audience: This course is geared for Python experienced developers, analysts or others who are build and train the latest and greatest deep learning models and contribute to making a dent in the world.

Course Snapshot 

  • Duration: 4 days 
  • Skill-level: Foundation-level Deep Learning with PyTorch skills for Intermediate skilled team members. This is not a basic class. 
  • Targeted Audience: This course is geared for Python experienced developers, analysts or others who are build and train the latest and greatest deep learning models and contribute to making a dent in the world.  
  • Hands-on Learning: This course is approximately 50% hands-on lab to 50% lecture ratio, combining engaging lecture, demos, group activities and discussions with machine-based student labs and exercises. Student machines are required. 
  • Delivery Format: This course is available for onsite private classroom presentation, or remote instructor led delivery, or CBT/WBT (by request). 
  • Customizable: This course may be tailored to target your specific training skills objectives, tools of choice and learning goals. 

Deep Learning with PyTorch teaches you how to implement deep learning algorithms with Python and PyTorch. This course takes you into a fascinating case study: building an algorithm capable of detecting malignant lung tumors using CT scans. As the authors guide you through this real example, you’ll discover just how effective and fun PyTorch can be. After a quick introduction to the deep learning landscape, you’ll explore the use of pre-trained networks and start sharpening your skills on working with tensors. You’ll find out how to represent the most common types of data with tensors and how to build and train neural networks from scratch on practical examples, focusing on images and sequences. After covering the basics, the course will take you on a journey through larger projects. The centerpiece of the course is a neural network designed for cancer detection. You’ll discover ways for training networks with limited inputs and start processing data to get some results. You’ll sift through the unreliable initial results and focus on how to diagnose and fix the problems in your neural network. Finally, you’ll look at ways to improve your results by training with augmented data, make improvements to the model architecture, and perform other fine tuning.! 

Working in a hands-on learning environment, led by our Deep Learning with PyTorch expert instructor, students will learn about and explore: 

  • you’ll explore the use of pre-trained networks and start sharpening your skills on working with tensors.  
  • You’ll find out how to represent the most common types of data with tensors and how to build and train neural networks from scratch on practical examples, focusing on images and sequences.  
  • After covering the basics, the course will take you on a journey through larger projects. 

Topics Covered: This is a high-level list of topics covered in this course. Please see the detailed Agenda below 

  • Using the PyTorch tensor API 
  • Understanding automatic differentiation in PyTorch 
  • Training deep neural networks 
  • Monitoring training and visualizing results 
  • Implementing modules and loss functions 
  • Loading data in Python for PyTorch 
  • Interoperability with NumPy 
  • Deploying a PyTorch model for inference 

Audience & Pre-Requisites 

This course is geared for attendees with Python skills who wish that how to implement deep learning algorithms with Python and PyTorch 

Pre-Requisites:  Students should have  

  • developers with some knowledge of Python as well as basic linear algebra skills.  
  • Some understanding of deep learning will be helpful 
  • No experience with PyTorch or other deep learning frameworks is required.  
  • Basic Linux skills, including familiarity with command-line options such as ls, cd, cp, and su 

Course Agenda / Topics 

  1. Introducing Deep Learning and the PyTorch Library 
  • What is PyTorch? 
  • What is this course? 
  • Why PyTorch 
  • competitive landscape 
  • 1.4 PyTorch has the batteries included 
  1. Pre-Trained Networks 
  • A pre-trained network that recognizes the subject of an image 
  • A pre-trained model that fakes it until it makes it 
  • A pre-trained network that describes scenes 
  • Torch Hub 
  1. Ch 3: It Starts with a Tensor 
  • Tensors are multi-dimensional arrays 
  • Indexing Tensors 
  • Named Tensors 
  • Tensor element types 
  • The tensor API 
  • Tensors — scenic views on storage 
  • Tensor metadata: size, offset, stride 
  • NumPy interoperability 
  • Moving tensors to the GPU 
  • Generalized Tensors are Tensors, too 
  • Serializing tensors 
  1. Real-World Data Representation Using Tensors 
  • Images 
  • Volumetric Data 
  • Tabular Data 
  • Time Series 
  • Text 
  1. The Mechanics of Learning 
  • Learning is just parameter estimation 
  • PyTorch’s Auto grad: Back-propagate all things 
  1. Using A Neural Network to Fit the Data 
  • Artificial Neurons 
  • The PyTorch nn module 
  • Sub classing nn. Module 
  1. Telling Birds from Airplanes: Learning from Images 
  • A dataset of tiny images 
  • Distinguishing birds from airplanes 
  1. Using Convolutions to Generalize 
  • The case for convolutions 
  • Convolutions  
  • Sub classing nn. Module 
  • Training our Convnet 
  • Model Design 

Part 2: Learning from Images in the Real-World: Early Detection of Lung Cancer 

  1. Using PyTorch To Fight Cancer 
  • What is a CT scan, exactly? 
  • The project: an end-to-end malignancy detector for lung cancer 
  1. Ready, Dataset, Go! 
  • Parsing LUNA’s annotation data 
  • Loading individual CT scans 
  • Locating a nodule using the patient coordinate system 
  • A straightforward Dataset implementation 
  1. Training A Classification Model to Detect Suspected Tumors 
  • The main entry point for our application 
  • Pre-training setup and initialization 
  • Our first-pass neural network design 
  • Training and validating the model 
  • Outputting performance metrics 
  • Running the training script 
  • Evaluating the model: Getting 99.7% correct means we’re done, right? 
  • Graphing training metrics with Tensor Board 
  • Why is the model not learning to detect malignant tumors? 
  1. Monitoring Metrics: Precision, Recall, and Pretty Pictures 
  • Good dogs versus bad guys: false positives and false negatives 
  • Graphing the positives and negatives 
  • What does an ideal data set look like? 
  • Revisiting the problem of over-fitting 
  • Data Augmentation 
  1. Using Segmentation to Find Suspected Nodules 
  • Segmentation is per-pixel classification 
  • A 3D Dataset in 2D 
  • Updating the training script 
  1. Deploying to production 
  • Serving PyTorch models 
  • Exporting Models 
  • Interacting with the PyTorch JIT 
  • LibTorch — PyTorch in C++ 
  • Emerging Technology: Enterprise serving of PyTorch models 
  • Going mobile 
View All Courses

    Course Inquiry

    Fill in the details below and we will get back to you as quickly as we can.

    Interested in any of these related courses?