philipp

Excited to introduce HypLL, our brand-new hyperbolic learning library developed together with @phippli and @PascalMettes! 1/4

Two years ago we released our open source framework for self supervised learning github.com/lightly-ai/lig…. Today it's used by leading tech companies and research institutions all over the world, reached almost 2k GitHub stars and has been installed over 100k times.

We added support for the Masked Siamese Network (MSN) to @lightly. MSN learns image representations by comparing cluster assignments of masked and unmasked image views. Great work by @mcaron31 @p_bojanowski @imisra_ @armandjoulin docs.lightly.ai/examples/msn.h… github.com/lightly-ai/lig…

Finally published @MSSEonline 👇 We developed and evaluated a deep learning approach to automatically segment anatomical cross-sectional area in panoramic ultrasound images of lower limb muscles. 🙏 @ritpau @MVFranchi @FabioSarto3 @NeilJCronin84 @phippli journals.lww.com/acsm-msse/abst…

A friend just shared this with me. A great example for how deep learning models struggle with out-of-distribution data. I wonder how many carriages the model has seen during training 😅

Open access code & GUI ✅ + Instructional video 📹: youtube.com/watch?v=It9CqV… 👌🏼⤵️

Open source, @PyTorch, @PyTorchLightnin, self-supervision, and models from @facebookai and other labs, these are a few of my favorite things... Good luck Lightly! github.com/lightly-ai/lig…

Collaboration with @Arm: Embedded covid mask detection on an Arm Cortex-M7 processor using @PyTorch. From self-supervised pre-training to transfer learning, conversion to TensorFlow Lite, quantization, and running it on the device. All summarized here: lightly.ai/post/embedded-…

@sidml12 @rasbt Thank you for your input! It's on my todo list - I will let you know when the update is ready :)

"Which Optimizer should I use for my Machine Learning Project?" whattolabel.com/post/which-opt… That's a neat quick reference table (personally, I am lazy and usually just stick to ADAM with default settings, works pretty well out of the box most of the time):

Thanks so much for sharing my blog post!