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.

banner-img

Course Skill Level:

Intermediate to Advanced

Course Duration:

4 day/s

  • Course Delivery Format:

    Live, instructor-led.

  • Course Category:

    AI / Machine Learning

  • Course Code:

    DLWPTOL21E09

Who should attend & recommended skills:

Those with basic Python, Linux, & linear algebra experience seeking to learn implementation of deep learning algorithms with Python and PyTorch

Who should attend & recommended skills

  • This course is geared for Python experienced developers, analysts or others who build and train the latest and greatest deep learning models and contribute to making a dent in the world and who wish to learn how to implement deep learning algorithms with Python and PyTorch.
  • Skill-level: Foundation-level Deep Learning with PyTorch skills for Intermediate skilled team members. This is not a basic class.
  • Python: Basic (1-2 years’ experience)
  • Linear Algebra: Basic (1-2 years’ experience)
  • Linux: Basic (1-2 years’ experience), including familiarity with command-lineoptions such as ls, cd, cp, and su
  • Deep Learning: Basic (1-2 years’ experience) helpful
  • PyTorch or other deep learning frameworks: Not required

About this course

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!

Skills acquired & topics covered

  • Working in a hands-on learning environment, led by our Deep Learning with PyTorch expert instructor, students will learn about and explore:
  • The use of pre-trained networks and start sharpening your skills on working with tensors
  • 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
  • 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
  • After covering the basics, the course will take you on a journey through larger projects

Course breakdown / modules

  • What is PyTorch?
  • What is this course?
  • Why PyTorch
  • competitive landscape
  • 1.4 PyTorch has the batteries included

  • 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

  • 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

  • Images
  • Volumetric Data
  • Tabular Data
  • Time Series
  • Text

  • Learning is just parameter estimation
  • PyTorch Auto grad: Back-propagate all things

  • Artificial Neurons
  • The PyTorch Module
  • Sub classing Module

  • A dataset of tiny images
  • Distinguishing birds from airplanes

  • The case for convolutions
  • Convolutions
  • Sub classing Module
  • Training our Convnet
  • Model Design

  • What is a CT scan, exactly?
  • The project: an end-to-end malignancy detector for lung cancer

  • Parsing LUNA annotation data
  • Loading individual CT scans
  • Locating a nodule using the patient coordinate system
  • A straightforward Dataset implementation

  • 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 are done, right?
  • Graphing training metrics with Tensor Board
  • Why is the model not learning to detect malignant tumors?

  • 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

  • Segmentation is per-pixel classification
  • A 3D Dataset in 2D
  • Updating the training script

  • Serving PyTorch models
  • Exporting Models
  • Interacting with the PyTorch JIT
  • LibTorch and PyTorch in C++
  • Emerging Technology: Enterprise serving of PyTorch models
  • Going mobile