Can a Gemini LLM beat StepLR for ResNet-18 on CIFAR-10?

I wanted to see if a Gemini LLM, called once per epoch, could pick a better learning rate than a fixed StepLR schedule for ResNet-18 on CIFAR-10.

Zero trust data pipeline framework

We have all experienced the pain of data loss or data incorrectness in our batch data pipelines. To address this, I designed a framework for ensuring data correctness at every stage o...

Asyncio_to_thread

Optimizing Python Asyncio Performance with asyncio.to_thread

Model inference in seldon kubernetes cluster

In this blog post, I’m sharing my journey of installing Seldon Core from scratch on my Mac. I started by setting up a local Kubernetes cluster and installing all the necessary depende...

Synthetic data generation

In my current organization, I am working on a model to sort post-consumer clothes to make them easier to recycle into products of different grades.

Dockerize whisper model

IntroductionWhat is a whisper model?Whisper is an open source speech recognition model trained by OpenAI. It enables transcription in multiple languages, as well as translation from t...

tsai model inference

Training LLM

Tunable loss functions for binary classification problems

Paper: Xtreme Margin: A Tunable Loss Function for Binary Classification Problems