Featured Resource
Featured Case Study
Deep Learning Fundamentals with PyTorch and FiftyOne
NVIDIA DLI Certification Workshop for Academia
April 5-6, 2025 | 10 AM – 5 PM CET
When and Where
- April 5-6, 2025
- 10 AM to 5 PM CET
- Workshops are delivered over Zoom
Register for the Zoom
This course is only available to university students, researchers and teaching staff. A valid university email address is required to register and obtain a certificate.
About the Workshop
Note: This course is only available to university students, researchers and teaching staff. A valid university email address is required to register and obtain a certificate.
This two day workshop is an extension of NVIDIA’s DLI Deep Learning Fundamentals Course.
Learn to implement neural networks for image classification from scratch using PyTorch. Learn about stochastic gradient descent, multilayer perceptrons, convolutional neural networks, and transformers. On day two, we will explore data augmentation, workflow management, and dataset curation using FiftyOne, a powerful open source tool for image dataset curation.
On the first day we will focus on building and training neural networks with PyTorch.
On the second day we will focus on visual dataset curation with FiftyOne and iterative improvement of image classification models.
Prerequisites
A basic knowledge of programming and high-school level math is sufficient to follow the course.
Programming Prerequisites: Python Fundamentals
Mathematics Prerequisites: Statistics and Probability
Mathematics Prerequisites: Linear Algebra
Mathematics Prerequisites: Calculus
Technologies Used in the Workshop
Assessment Type
Skills-based coding assessments evaluate students’ ability to train a deep learning model to classify images with high accuracy.
Certificate
Upon successful completion of the coding assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.
Hardware Requirements
Desktop or laptop computer capable of running the latest version of Chrome or Firefox. Each participant will be provided with dedicated access to a fully configured, GPU-accelerated server in the cloud.
Language
English
Schedule
Day 1
- Introduction (15 mins)
- The Mechanics of Deep Learning (120 mins)
- Break (60 mins)
- Pre-trained Models and Fundamentals of Transformers (120 mins)
- Break (15 mins)
- Project: Fine-tuning and Data Augmentation (120 mins)
- Day 1 Review (30 mins)
Day 2
- Introduction to FiftyOne (90 mins)
- Data Curation Fundamentals (90 mins)
- Break (60 mins)
- Model Evaluation with FiftyOne (90 mins)
- Advanced Dataset Workflows (90 mins)
- Final Project: Building an End-to-End Workflow (60 mins)
- Break (15 min)
- Closing and Certification Review (30 mins)
Further Reading
PyTorch Resources
- Practical Computer Vision with PyTorch and FiftyOne
- PyTorch Official Tutorials
- PyTorch Documentation
- PyTorch Cheat Sheet
- 60-Minute Blitz Tutorial
- PyTorch Examples Repository
- PyTorch Vision Models
FiftyOne Resources
About the Instructor
Antonio Rueda-Toicen
Voxel51
Antonio Rueda-Toicen, an AI Engineer in Berlin, has extensive experience in deploying machine learning models and has taught over 300 professionals. He is currently a Research Scientist at the Hasso Plattner Institute. Since 2019, he has organized the Berlin Computer Vision Group and taught at Berlin’s Data Science Retreat. He specializes in computer vision, cloud technologies, and machine learning. Antonio is also a certified instructor of deep learning and diffusion models in NVIDIA’s Deep Learning Institute.