Training > AI/Machine Learning > PyTorch Essentials: An Applications-First Approach (LFD273)

Training Course

Start prototyping AI applications powered by PyTorch by leveraging popular pretrained models in the fields of Computer Vision and Natural Language Processing covering an extensive span of practical applications.

Who Is It For

This course is designed for machine learning practitioners who want to add deep learning models in PyTorch – especially pretraining models for Computer Vision and Natural Language Processing – to quickly prototype and deploy applications.

read less read more

What You’ll Learn

The course begins with an overview of PyTorch, including model classes, datasets, data loaders and the training loop. Next, it covers the role and power of transfer learning, along with how to use it with pretrained models. Practical lab exercises cover multiple topics including: image classification, object detection, sentiment analysis, text classification, and text generation/completion. Learners also will use their data to fine-tune existing models and leverage third-party APIs.

read less read more

What It Prepares You For

This course provides hands-on experience to train and fine-tune deep learning models using the rich PyTorch and Hugging Face ecosystems of pre-trained models for Computer Vision and Natural Language Processing tasks. Additionally, you will be able to deploy prototype applications using TorchServe, allowing you to quickly validate and demo your application.

read less read more

Course Outline

Chapter 1. Course Introduction

Chapter 2. PyTorch, Datasets, and Models

Chapter 3. Building Your First Dataset

Chapter 4. Training Your First Model

Chapter 5. Building Your First Hugging Face Dataset

Chapter 6. Transfer Learning and Pretrained Models

Chapter 7. Pretrained Models for Computer Vision

Chapter 8. Pretrained Models for Natural Language Processing

Chapter 9. Image Classification with Torchvision

Chapter 10. Fine-Tuning Pretrained Models for Computer Vision

Chapter 11. Serving Models with TorchServe

Chapter 12. Datasets and Transformations for Object Detection and Image Segmentation

Chapter 13. Models for Object Detection and Image Segmentation

Chapter 14. Object Detection Evaluation

Chapter 15. Word Embeddings and Text Classification

Chapter 16. Contextual Word Embeddings with Transformers

Chapter 17. Hugging Face Pipelines for NLP Tasks

Chapter 18. Q&A, Summarization, and LLMs

Prerequisites

To get the most possible value from this course, you should be familiar with the following:

Python (notions of Object-Oriented Programming (OOP))
PyData Stack (Numpy – arrays, slicing, vectorized operations – , Pandas – series, slicing, indexing, transformations – , Matplotlib – basic plotting only – , Scikit-Learn – linear regression, pipelines, one-hot encoding, normalization/scaling, grid search, hyper-parameter optimization)
Machine Learning Concepts (supervised learning: regression and classification; loss functions: RMSE, cross-entropy; train-validation-test split; evaluation metrics (R-squared, precision, recall, accuracy, confusion matrix)

Lab Info

To do the lab exercises in this course, you’ll need the following:

Google account (for Google Colab, free tier)

Reviews

Jul 2024

I like the different types of approach to training models highlighted, like just taking the pipelines, or taking the model and changing its head, or just making a model from scratch.

May 2024

Every chapter was really instructive. Thanks!

Dec 2023

The content was solid, while providing references to dive much deeper.