Marc Romeyn's Projects
π A UI Design Language
LIΒ³DS Rest API
Automated machine learning for analytics & production
An opinionated kit to provide people some inspiration and ideas for their own workflows.
Deep learning operations reinvented (supports tf, pytorch, chainer, gluon and others)
All 3 assignments that were given during the Flink workshop
GRU4Rec is the cleaned & simplified implementation of the algorithm of the "Session-based Recommendations with Recurrent Neural Networks" paper, published at ICLR 2016. The code is stripped of features that we had found to be unhelpful in increasing accuracy.
A simple Chrome extension that adds a button to your browser toolbar which, when clicked, will export your Instapaper highlights as an HTML page (with JSON output included).
Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow.
Light OpenSource PointCloud Server
Ongoing research training transformer models at scale
Model analysis tools for TensorFlow
Merlin Models is a collection of deep learning recommender system model reference implementations
NeMo: a toolkit for conversational AI
NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.
NYU Deep Learning Spring 2021
Machine Learning Pipelines for Kubeflow
Learning to Rank in TensorFlow
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
TFX is an end-to-end platform for deploying production ML pipelines
TorchX is a universal job launcher for PyTorch applications. TorchX is designed to have fast iteration time for training/research and support for E2E production ML pipelines when you're ready.
Input pipeline framework