talk-data.com

Praktische Session zu ChromeOS Flex.

In this episode, Conor and Bryce record live from NDC TechTown in Norway! We interview Vittorio Romeo and JF Bastien about C++, training, their talks and more! Link to Episode 259 on WebsiteDiscuss this episode, leave a comment, or ask a question (on GitHub)Socials ADSP: The Podcast: TwitterConor Hoekstra: Twitter | BlueSky | MastodonBryce Adelstein Lelbach: TwitterAbout the Guests: Vittorio is a passionate C++ expert with over a decade of professional and personal experience. His expertise covers library development, high-performance financial backends, game development, open-source contributions, and active participation in ISO C++ standardization. He is the coauthor of "Embracing Modern C++ Safely" and is a speaker at over 25 international conferences. JF Bastien has worked on hardware, compilers, security, performance, web browsers, and airplanes. As chair of the C++ language evolution working group and co-designer of WebAssembly, his contributions have helped shape modern software development. Show Notes Date Recorded: 2025-09-24 Date Released: 2025-11-07 camomilla by Vittorio Romeoromeo.trainingRoku rostdASDP Episode 136: 🇬🇧 C++ On Sea Live 🇬🇧 CppCast, TLB HIT & Two's Complement!TLB.hitJAXOpenXLA[LATTE '22] Chris Leary: X-istentialism: Supercomputers, Silicon Atoms, and the Science Between!Guest Lecture - XLS (Chris Leary)Project DenverIntel pays NVIDIA $1.5BNDC TechTown JF Talk(char)0 = 0; - What Does the C++ Programmer Intend With This Code? - JF Bastien - C++ on Sea 2023Keynote: Safety and Security: The Future of C++ - JF Bastien - CppNow 2023All the Safeties: Safety in C++ - Sean Parent - CppNow 2023NDC TechTown Vittorio Romeo TalkMore Speed & Simplicity: Practical Data-Oriented Design in C++ - Vittorio Romeo - CppCon 2025CppCon 2014: Mike Acton "Data-Oriented Design and C++"Intro Song Info Miss You by Sarah Jansen https://soundcloud.com/sarahjansenmusic Creative Commons — Attribution 3.0 Unported — CC BY 3.0 Free Download / Stream: http://bit.ly/l-miss-you Music promoted by Audio Library https://youtu.be/iYYxnasvfx8

Hyperparameter optimization using TerraTorch Iterate with Optuna for NAS and HPO.

Finetuning and Inference.

Benchmarking foundation models in geospatial AI using TerraTorch and GEO-Bench.

Discussion of geospatial computer vision foundation models.

Finetuning and Inference

An overview of geospatial computer vision foundation models and their role in research and practice.

A short recap on CUDA, PyTorch and Lightning.

Benchmarking foundation models

Hyperparameter Optimization with TerraTorch Iterate using Optuna

Benchmarking foundation models.

Hyperparameter Optimization with TerraTorch Iterate and Optuna.

Hyper Parameter Optimization, Neural Architecture Search and Foundation Model Benchmarking using TerraTorch for (geospatial) computer vision TerraTorch is a fine-tuning and benchmarking toolkit for Geospatial Foundation Models built on PyTorch Lightning and tailored for satellite, weather, and climate data. It integrates domain-specific data modules, pre-defined tasks, and a modular model factory that pairs any backbone with diverse decoder heads. These components allow researchers and practitioners to fine-tune supported models in a no-code fashion by simply editing a training or inference configuration. By consolidating best practices for model development and incorporating the automated hyperparameter optimization extension Iterate, TerraTorch reduces the expertise and time required to fine-tune or benchmark models on new Earth Observation use cases. Furthermore, TerraTorch directly integrates with GEO-Bench, allowing for systematic and reproducible benchmarking of Geospatial Foundation Models. TerraTorch Iterate is not only driving GeoBench, but also Hyperparameter Optimizations (HPO) and Neural Architecture Search (NAS). TerraTorch is open sourced under Apache 2.0, and can be installed via pip install terratorch from our Github repostitory.

Highlights

• Growing list of IBM and community Out-of-the-box implementations of foundation models (e.g.Prithvi, Satlas, Clay, timm models) and a large selection of decoders
• Model fine-tuning fully accessible through config files – no need to write code for segmentation, pixel-wise regression, object detection or classification tasks
• The functionalities of TerraTorch are a superset of Lightning and TorchGeo. All the goodies from these libraries come for free

Agenda

1. Welcome & introductions
2. Short recap on cuda, torch and lightning
3. What are (geospatial) computer vision foundation models
4. Finetuning and Inference
5. Hyperparameter Optimization with terratorch iterate using optuna
6. Benchmarking foundation models
7. Q&A
8. Closing

About the speaker Romeo is an AI Research Engineer at IBM Research Europe in Zurich interested in understanding neural representations in artificial and biological neural networks.

About the AI Alliance The AI Alliance is an international community of researchers, developers and organizational leaders committed to support and enhance open innovation across the AI technology landscape to accelerate progress, improve safety, security and trust in AI, and maximize benefits to people and society everywhere. Members of the AI Alliance believe that open innovation is essential to develop and achieve safe and responsible AI that benefit society rather than benefit a select few big players.

Hyper Parameter Optimization, Neural Architecture Search and Foundation Model Benchmarking using TerraTorch for (geospatial) computer vision TerraTorch is a fine-tuning and benchmarking toolkit for Geospatial Foundation Models built on PyTorch Lightning and tailored for satellite, weather, and climate data. It integrates domain-specific data modules, pre-defined tasks, and a modular model factory that pairs any backbone with diverse decoder heads. These components allow researchers and practitioners to fine-tune supported models in a no-code fashion by simply editing a training or inference configuration. By consolidating best practices for model development and incorporating the automated hyperparameter optimization extension Iterate, TerraTorch reduces the expertise and time required to fine-tune or benchmark models on new Earth Observation use cases. Furthermore, TerraTorch directly integrates with GEO-Bench, allowing for systematic and reproducible benchmarking of Geospatial Foundation Models. TerraTorch Iterate is not only driving GeoBench, but also Hyperparameter Optimizations (HPO) and Neural Architecture Search (NAS). TerraTorch is open sourced under Apache 2.0, and can be installed via pip install terratorch from our Github repostitory.

Highlights

• Growing list of IBM and community Out-of-the-box implementations of foundation models (e.g.Prithvi, Satlas, Clay, timm models) and a large selection of decoders
• Model fine-tuning fully accessible through config files – no need to write code for segmentation, pixel-wise regression, object detection or classification tasks
• The functionalities of TerraTorch are a superset of Lightning and TorchGeo. All the goodies from these libraries come for free

Agenda

1. Welcome & introductions
2. Short recap on cuda, torch and lightning
3. What are (geospatial) computer vision foundation models
4. Finetuning and Inference
5. Hyperparameter Optimization with terratorch iterate using optuna
6. Benchmarking foundation models
7. Q&A
8. Closing

About the speaker Romeo is an AI Research Engineer at IBM Research Europe in Zurich interested in understanding neural representations in artificial and biological neural networks.

About the AI Alliance The AI Alliance is an international community of researchers, developers and organizational leaders committed to support and enhance open innovation across the AI technology landscape to accelerate progress, improve safety, security and trust in AI, and maximize benefits to people and society everywhere. Members of the AI Alliance believe that open innovation is essential to develop and achieve safe and responsible AI that benefit society rather than benefit a select few big players.

Hyper Parameter Optimization, Neural Architecture Search and Foundation Model Benchmarking using TerraTorch for (geospatial) computer vision TerraTorch is a fine-tuning and benchmarking toolkit for Geospatial Foundation Models built on PyTorch Lightning and tailored for satellite, weather, and climate data. It integrates domain-specific data modules, pre-defined tasks, and a modular model factory that pairs any backbone with diverse decoder heads. These components allow researchers and practitioners to fine-tune supported models in a no-code fashion by simply editing a training or inference configuration. By consolidating best practices for model development and incorporating the automated hyperparameter optimization extension Iterate, TerraTorch reduces the expertise and time required to fine-tune or benchmark models on new Earth Observation use cases. Furthermore, TerraTorch directly integrates with GEO-Bench, allowing for systematic and reproducible benchmarking of Geospatial Foundation Models. TerraTorch Iterate is not only driving GeoBench, but also Hyperparameter Optimizations (HPO) and Neural Architecture Search (NAS). TerraTorch is open sourced under Apache 2.0, and can be installed via pip install terratorch from our Github repostitory.

Highlights

• Growing list of IBM and community Out-of-the-box implementations of foundation models (e.g.Prithvi, Satlas, Clay, timm models) and a large selection of decoders
• Model fine-tuning fully accessible through config files – no need to write code for segmentation, pixel-wise regression, object detection or classification tasks
• The functionalities of TerraTorch are a superset of Lightning and TorchGeo. All the goodies from these libraries come for free

Agenda

1. Welcome & introductions
2. Short recap on cuda, torch and lightning
3. What are (geospatial) computer vision foundation models
4. Finetuning and Inference
5. Hyperparameter Optimization with terratorch iterate using optuna
6. Benchmarking foundation models
7. Q&A
8. Closing

About the speaker Romeo is an AI Research Engineer at IBM Research Europe in Zurich interested in understanding neural representations in artificial and biological neural networks.

About the AI Alliance The AI Alliance is an international community of researchers, developers and organizational leaders committed to support and enhance open innovation across the AI technology landscape to accelerate progress, improve safety, security and trust in AI, and maximize benefits to people and society everywhere. Members of the AI Alliance believe that open innovation is essential to develop and achieve safe and responsible AI that benefit society rather than benefit a select few big players.