At the beginning of August, we’d love to invite you to join us in the next tinyML Shenzhen meetups at 8：00 PM on August 11 (GMT+8). We’ll have Jelmer Neeven, who is a deep learning scientist and software engineer, share about Data Techniques That Enable Tiny Computer Vision in the Real World.
Production-worthy computer vision models need large quantities of high-quality training data, even when the models themselves are tiny. Plumerai’s fully in-house data tooling therefore leverages several powerful machine learning techniques, allowing us to build and curate datasets with millions of images.
In this talk, Jelmer will demonstrate how these tools allow us to identify and address issues in our dataset that negatively affect our models, for example by inspecting images that contributed strongly to a specific false prediction during training. He will also cover the other essential parts of our model and data pipelines, which together allow us to build accurate person detection models that run on the tiniest edge devices.
⌚️Time: 02:00 PM – 03:00 PM (CET) // 08:00-09:00 PM (GMT +8),August 11, 2022
🎤Talk theme: Data techniques that enable tiny computer vision in the real world
About the Speaker
Jelmer Neeven is a deep learning scientist and software engineer at Plumerai with a passion for building smart tools and real-world AI applications. He obtained an MSc in AI from Maastricht University and has been with Plumerai for three years. He spends his time building efficient and robust AI for microcontrollers through researching novel model architectures, data techniques and training methods.
That’s all for today’s post. As always, we can’t wait to see what you‘re tinkering with lately. Shoot us a tweet @seeedstudio, or let us know on LinkedIn, Discord, or publish your project on our Project Hub on Hackster. Please be safe out there, be kind to one another, and we’ll see you next time!