Hi! So far I've specialized in medical segmentation and optimization algorithms, but done a lot of other stuff as well. My master's thesis was in glioblastoma segmentation on MRI images using neural nets.
If you are into optimization, you might find pytorch image descent useful for debugging and quickly visualizing momentum or generally how an optimizer works. I've also implemented some gradient-free PyTorch optimizers in torchzero (pretty sure its the first library to do so!), which is useful when you need to optimize a function or a model without having access to gradients.
My first every project was a music beat swapping and automatic mixing/remixing tool with AI-based beat detection which you can try in your browser https://huggingface.co/spaces/dpe1/beat_manipulator.
- discord https://discord.com/users/356441827097968640
- telegram https://t.me/stunlocked
- email nkshv2@gmail.com