Training > AI/Machine Learning > PyTorch in Practice: An Applications-First Approach (LFD473)

PyTorch in Practice: An Applications-First Approach (LFD473)

Start prototyping AI applications powered by PyTorch, one of the most popular deep learning frameworks, 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 protype 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 the role and power of transfer learning is addressed 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
Expand All
Collapse All
- Who You Are
- Who we are
- Copyright and No Confidential Information
- Training
- Certification Programs and Digital Badging
PyTorch, Datasets, and Models
- What is PyTorch
- The PyTorch Ecosystem
- Supervised vs Unsupervised Learning
- Software Development vs Machine and Deep Learning
- "Hello Model"
- Naming Is Hard
- Setup and Environment
Building Your First Dataset
- Tensors, Devices, and CUDA
- Datasets
- Dataloaders
- Datapipes
- Lab 1A: Non-Linear Regression
Training Your First Model
- Recap
- Models
- Loss Functions
- Gradients and Autograd
- Optimizers
- The Raw Training Loop
- Evaluation
- Saving and Loading Models
- NonLinearities
- Lab 1B: Non-Linear Regression
Building Your First Datapipe
- A New Dataset
- Datapipes
- Lab 2: Price Prediction
- Tour of High Level Libraries
- Tour of High-Level Libraries
Transfer Learning and Pretrained Models
- What is Transfer Learning?
- Torch Hub
- Computer Vision
- Dropout
- ImageFolder Dataset
Pretrained Models for Computer Vision
- PyTorch Image Models
- HuggingFace
Natural Language Processing
- Natural Language Processing
- One Logit or Two Logits?
- Cross-Entropy Loss
- TensorBoard
- Sentiment Analysis
- Hugging Face Pipelines
- Generative Models
Image Classification with Torchvision
- Torchvision
- Pretrained Models as Feature Extractors
Fine-Tuning Pretrained Models for Computer Vision
- Fine Tuning Pretained Models
Serving Models with TorchServe
- Archiving and Serving Models
- TorchServe
- Zero-Shot Image Classification
Datasets and Transformations for Object Detection and Image Segmentation
- Object Detection, Image Segmentation, and Keypoint Detection
- Bounding Boxes
- Torchvision Operators
- Transforms (V2)
- Custom Dataset for Object Detection
Models for Object Detection and Image Segmentation
- Models
Models for Object Detection Evaluation
- Recap
- Making Predictions
- Evaluation
- HuggingFace Pipelines for Object Detection
- Zero-Shot Object Detection
Word Embeddings and Text Classification
- Torchtext
- AG News Dataset
- Tokenization
- Embeddings
- Vector Databases
- Zero-Shot Text Classification
Contextual Word Embeddings with Transformers
- Attention is All You Need
- Transformer
- An Encoder-Based Model for Classification
- Contextual Embeddings
Huggingface Pipelines for NLP Tasks
- HuggingFace Pipelines
Question and Answer, Summarization, and LLMs
- EDGAR Dataset
- Hallucinations
- Asymmetric Semantic Search
- ROUGE Score
- Decoder-Based Models
- Large Language Models (LLMs)
Closing and Evaluation Survey
- Evaluation Survey

While there are no formal prerequisites, students should have some knowledge of Python (notions of object-oriented programming), PyData Stack (Numpy, Pandas, Matplotlib, Scikit-Learn), and Machine Learning concepts (supervised learning, loss functions, train-validation-test split, evaluation metrics).