Lukas Geiger

@KyleRayKelley @rahuldave @zeddotdev Feels like it's becoming a habit... The first lines I write in any new language absolutely need to be a PR for @KyleRayKelley to review 🤣 Last time it was JS/CoffeScript this time Rust 🦀😎

@rahuldave @zeddotdev @_lgeiger also couldn't wait -- he's making PRs github.com/zed-industries…

Sneak peek of native notebook UI in @zeddotdev

@KyleRayKelley @zeddotdev @AtomEditor @nteractio Just looked at some old screenshots. Looks like we were copying what ipython did. However, ipython only showed `In[*]` starting version in 8. Before that it would look something like `<ipython-input-1-6fcf9dfbd479> in <module>()` so even ipython didn't have line numbers.

Did Hydrogen in Atom show line numbers in replacement for `In[*]`? @_lgeiger

@KyleRayKelley @nathansobo @zeddotdev @cursor_ai @KyleRayKelley our last chat actually got me thinking about the same thing. Zed+AI+Hydrogen would be a pretty sweet combo 🤔

Indexing and retrieval of my local code base as well as documentation from outside sources. I'd love to be able to plop a link to a crate or PyPI project to help me and the LLM discover what's available to work with. I also want to be able to go straight from an inline error to chat/fix. By the way, any plan for interpreters? We should chat. The world needs Hydrogen again. 😁

The editing experience in @zeddotdev is *perfect* while the AI-enabled search in @cursor_ai is incredibly good. I wish the two would get married.

We made our ultra-fast and ultra-small inference engine for Arm Cortex-M processors even smaller. We now require 49% less RAM for 8-bit MobileNetV2 than TensorFlow Lite for Microcontrollers with Arm’s CMSIS-NN kernels. Read the article here: blog.plumerai.com/2021/10/cortex…

🏆 We built the world’s fastest and most memory-efficient deep learning inference software for Arm Cortex-M microcontrollers 🏆 for both Binarized Neural Networks and for 8-bit deep learning models. blog.plumerai.com/2021/10/cortex…

Our latest paper has been accepted to the #MLSys2021 conference! Congratulations Tom, Arash, Adam, Lukas, Tim, Leon, Jelmer and Koen! We wrote a short blog post about the paper and the importance of Larq Compute Engine: blog.plumerai.com/2021/04/mlsys2…

It was great to see so many people attending our #tinyml webcast earlier this week! In case you missed the event, a recording of the talk is now online along with a short blog post explaining the main takeaways from our presentation: blog.plumerai.com/2021/01/tinyml…

A fascinating talk on binarized neural networks for #tinyml by Lukas of @plumerai is now up at youtube.com/watch?v=f9SNqD…, with slides at tinyml.org/wp-content/upl…

This is starting in a few hours, come join our #tinyML webcast!

Come join us on Tuesday for our @tinyMLTalks webcast! @_lgeiger will explain how we use 🚀Binarized Neural Networks🚀 to enable real-time deep learning on cheap, low-power edge devices. You can register here: us02web.zoom.us/webinar/regist…

We've released v0.4 of Larq Compute Engine! Some of our internal work optimizing BNN performance on microcontrollers has made its way to mobile and Raspberry Pi, as have a few major architectural improvements. 🚀 Full change log: github.com/larq/compute-e…

We just published blog post about open source tools for #DeepLearning presented at our social event at the @iclr_conf! Shout-out to all the co-authors for their great contributions and efforts. Without your help, this would not have been possible! neptune.ai/blog/iclr-2020… (1/n)

We’ve released Larq Compute Engine v0.3, featuring even faster BNN kernels and support for Python 3.8, TensorFlow 2.2, and Windows in the converter! 🎉 💻 Full release notes: github.com/larq/compute-e… 📚 Docs: docs.larq.dev/compute-engine/

The Larq Compute Engine team pushed out LCE v0.2.1 earlier today—same models, up to 15% lower latency. github.com/larq/compute-e…

@fchollet Improved contributor experience. Moving Keras out of the tf monorepo will hopefully help, but currently having to wait hours for tf to build on a laptop just for a small Python fix and then waiting weeks to get a PR review doesn't encourage community contributions.

@fchollet One recommended way to save and resume training - tf.train.Checkpoint is great but requires too much custom code - Model.save_weights and ModelCheckpoint don't reload optimizer state or epoch - Model.save doesn't play well with tf.distribute

What's a feature you wish Keras had?

We wrote a blog post about how we’re applying a software 2.0 approach in the new module for state-of-the-art binarized neural networks in Larq Zoo (`zoo.sota`). It also features some exciting improvements across the whole Larq stack: blog.larq.dev/2020/03/larq-e…

We’ve just released Larq v0.9, featuring: 🔲 Non-zero padding 💾 Easier export for binary weights 📋 Improved model summaries And lots more! 🎉 github.com/larq/larq/rele…

More about Larq Compute Engine: 📑 Docs: docs.larq.dev/compute-engine 👩‍💻 GitHub: github.com/larq/compute-e… 💱 MLIR converter: docs.larq.dev/compute-engine… 📱 Android deployment: docs.larq.dev/compute-engine… 🥧 Raspberry Pi deployment: docs.larq.dev/compute-engine…