LFD473 PyTorch in Practice: An Applications-First Approach

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.

Voraussetzungen

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).

Inhalt

Introduction

  • 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
  • Lab 2: Price Prediction
  • Tour of High Level Libraries

Transfer Learning and Pretrained Models

  • What is Transfer Learning?
  • Torch Hub
  • Computer Vision
  • Dropout
  • ImageFolder Dataset
  • Lab 3: Classifying Images

Pretrained Models for Computer Vision

  • PyTorch Image Models
  • HuggingFace

Natural Language Processing

  • Natural Language Processing
  • One Logit or Two Logits?
  • Cross-Entropy Loss
  • TensorBoard
  • Lab 4: Sentiment Analysis
  • Hugging Face Pipelines
  • Generative Models

Fine-Tuning Pretrained Models for Computer Vision

  • Fine Tuning Pretained Models
  • Zero-shot Image Classification

Serving Models with TorchServe

  • Archiving and Serving Models
  • TorchServe

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
  • Lab 5A: Fine-Tuning Object Detection Models

Models for Object Detection and Image Segmentation

  • Models
  • Lab 5B: Fine-Tuning Object Detection Models

Models for Object Detection Evaluation

  • Recap
  • Making Predictions
  • Evaluation
  • YOLO
  • 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
  • Chunking Strategies
  • Lab 6: Text Classification using Embeddings

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
  • Lab 7: Document Q&A

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

Kurszeiten

Wer möchte, reist bis 22 Uhr am Vortag an und nutzt den Abend bereits zum Fachsimpeln am Kamin oder im Park.

An Kurstagen gibt es bei uns ab 8 Uhr Frühstück.

Unsere Kurse beginnen um 9 Uhr und enden um 18 Uhr.

Neben den kleinen Pausen gibt es eine Stunde Mittagspause mit leckerem, frisch in unserer Küche zubereitetem Essen.

Nach der Schulung anschließend Abendessen und Angebote für Fachsimpeln, Ausflüge uvm. Wir schaffen eine Atmosphäre, in der Fachleute sich ungezwungen austauschen. Wer das nicht will, wird zu nichts gezwungen und findet auch jederzeit Ruhe.

Termine und Anmeldung

Es steht noch kein Termin für diesen Kurs fest.

Haben Sie einen Wunschtermin?

Verwandte Seminare ...

...