Uvadlc_notebooks

Visit Tool

uvadlc_notebooks is an open-source repository of Jupyter notebook tutorials for teaching deep learning. It provides practical implementations for the Deep Learning Course at the University of Amsterdam, supporting both PyTorch and JAX+Flax frameworks.

Claim this tool

No Views Yet

At a glance

Pricing

Free · Open Source

Free tier

Yes

API

Skill level

Technical

About

What is uvadlc_notebooks?

The uvadlc_notebooks repository offers a comprehensive collection of Jupyter notebook tutorials specifically designed for the Deep Learning Course at the University of Amsterdam (MSc AI). These notebooks aim to bridge the gap between theoretical concepts and practical implementation, covering diverse topics such as optimization techniques, transformers, graph neural networks, and more. The materials are available for both Fall 2023 and Fall 2024 course editions, with support for PyTorch and PyTorch Lightning, as well as JAX+Flax. Users can run the notebooks locally on CPU, utilize Google Colab for GPU access, or leverage the Snellius cluster for larger-scale training. The tutorials are integrated into PyTorch Lightning's official documentation, making them a valuable resource for students and practitioners alike.

Best used for

Ideal for students and teachers who need to grasp deep learning theory through hands-on coding, implement various neural network architectures, and experiment with both PyTorch and JAX+Flax frameworks. Especially valuable for those following the University of Amsterdam's Deep Learning Course or self-studying advanced AI topics.

Common actions

learn deep learning

implement neural networks

practice PyTorch

explore JAX Flax

low-code/no-codeworkflowscollaborationdeepfakeautomated workflowface swappingopen-source"AI Agents"github copilot

Capabilities

Key features

Jupyter notebook tutorials
PyTorch implementations
JAX+Flax implementations
Google Colab integration
Snellius cluster guidance
Pretrained models provided

Target Audience

studentteacherprofessor

Integrations

Not yet documented

Pricing & Plans

Free · Open Source

Free

FAQs

What deep learning topics are covered in the notebooks?

The notebooks cover a range of topics including optimization techniques, transformers, graph neural networks, deep energy models, autoencoders, adversarial attacks, normalizing flows, autoregressive image modeling, vision transformers, and meta-learning. This provides a broad overview of modern deep learning concepts.

Can these notebooks be run without a powerful GPU?

Yes, the notebooks are designed to be executable on common laptops without requiring a dedicated GPU for many examples. Pretrained models are provided, and you can use Google Colab for free GPU access if needed for more intensive tasks.

Are the notebooks available for different deep learning frameworks?

Yes, the tutorials provide implementations in both PyTorch (including PyTorch Lightning) and one-to-one translations to JAX+Flax. This allows users to learn and compare concepts across different popular deep learning frameworks.

Trending

Subcategories trending in Research & Education

Academic Research Study Assistants Knowledge Management Scientific Computing Summarization Language Learning

Trending

Also listed in

This tool also appears in

Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce