Michael Lanzetta's repositories
node-amqp10
amqp10 is a promise-based, AMQP 1.0 compliant node.js client
easy-tensorflow-multimodel-server
Simple to run server for multiple TensorFlow Object Detection models
NikkeiAISummit2019
Deck and supporting content for talk at Nikkei AI Summit - 2019.04.22
SocialGoodAtCloudScale
Social Good at Cloud Scale - a talk at MLPrague 2018, and supporting materials.
ImageRecognitionInKeras
A few simple scripts to help you train and evaluate Transfer Learning-based custom image recognition models.
MLTokyo2019Talk
Presentation and supporting materials for my talk to the MLTokyo group in November of 2019
node-cerulean
Wrappers, utilities, etc. for making working with Azure and Azure Storage even easier in Node.js
StrataDataLondon2018
Content for the talk Elena Terenzi and I gave at Strata Data in London on 24-May-2018.
aml-tf-object-detection-deployment
A sample Azure Machine Learning project for creating the Docker container with a pre-trained object detection model and deploying it as API
bingtilesystem
TypeScript/Node bing tile system stuffs
bt
bt - flexible backtesting for Python
code-with-engineering-playbook
This is the playbook for "code-with" customer or partner engagements
edgellm
LLMs on the Edge
langchain-ts-conversations
Testing ability of models to converse with themselves and self-correct
llm-challenger
Using LangChain.js to build intuition on how LLMs can self-correct and self-regulate.
MLOpsManufacturing
Demonstrate samples and good engineering practice for operationalizing machine learning solutions.
noodlefrenzy.github.io
Public site for Michael Lanzetta (noodlefrenzy), a Software Engineer, Data Scientist, and Manager at Microsoft.
Probabilistic-Programming-and-Bayesian-Methods-for-Hackers
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
PythonDataScienceHandbook
Jupyter Notebooks for the Python Data Science Handbook
semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
tuned-lens
Tools for understanding how transformer predictions are built layer-by-layer