Course Overview
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.
PyTorch in Practice: An Applications-First Approach (LFD473) is designed for machine learning practitioners who want to add deep learning models in PyTorch to their skill set. After successfully completing the course you will be able to fine tune deep learning models using 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 applications.
“AI skills are in high demand and short supply,” said Clyde Seepersad, SVP, General Manager, Training & Certification, Linux Foundation. “Adding PyTorch to your profile will significantly enhance your employability for the coming decade.”
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.
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.
Requirements
- 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).
Target audiences
- 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.
Curriculum
- 1 Section
- 19 Lessons
- 4 Days
- Topics19
- 1.1Introduction Who You Are Who we are Copyright and No Confidential Information Training Certification Programs and Digital Badging
- 1.2PyTorch, 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
- 1.3Building Your First Dataset Tensors, Devices, and CUDA Datasets Dataloaders Datapipes Lab 1A: Non-Linear Regression
- 1.4Training 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
- 1.5Building Your First Datapipe A New Dataset Lab 2: Price Prediction Tour of High Level Libraries
- 1.6Transfer Learning and Pretrained Models What is Transfer Learning? Torch Hub Computer Vision Dropout ImageFolder Dataset Lab 3: Classifying Images
- 1.7Pretrained Models for Computer Vision PyTorch Image Models HuggingFace
- 1.8Natural Language Processing Natural Language Processing One Logit or Two Logits? Cross-Entropy Loss TensorBoard Lab 4: Sentiment Analysis Hugging Face Pipelines Generative Models
- 1.9Image Classification with Torchvision Torchvision Pretrained Models as Feature Extractors
- 1.10Fine-Tuning Pretrained Models for Computer Vision Fine Tuning Pretained Models Zero-shot Image Classification
- 1.11Serving Models with TorchServe Archiving and Serving Models TorchServe
- 1.12Datasets 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 ab 5A: Fine-Tuning Object Detection Models
- 1.13Models for Object Detection and Image Segmentation Models Lab 5B: Fine-Tuning Object Detection Models
- 1.14Models for Object Detection Evaluation Recap Making Predictions Evaluation YOLO HuggingFace Pipelines for Object Detection Zero-Shot Object Detection
- 1.15Word Embeddings and Text Classification Torchtext AG News Dataset Tokenization Embeddings Vector Databases Zero-Shot Text Classification Chunking Strategies Lab 6: Text Classification using Embeddings
- 1.16Contextual Word Embeddings with Transformers Attention is All You Need Transformer An Encoder-Based Model for Classification Contextual Embeddings
- 1.17Huggingface Pipelines for NLP Tasks HuggingFace Pipelines Lab 7: Document Q&A
- 1.18Question and Answer, Summarization, and LLMs EDGAR Dataset Hallucinations Asymmetric Semantic Search ROUGE Score Decoder-Based Models Large Language Models (LLMs)
- 1.19Closing and Evaluation Survey Evaluation Survey
Instructor
