vowpal_wabbit

Potato is an AI-driven scientific operating system for life sciences. It helps researchers design and execute experiments by synthesizing literature and generating lab protocols. Potato supports computational analyses, data workflows, and parallel experimental variations. It accelerates scientific execution for individual researchers, teams, and large organizations.

advanced_lane_detection is a computer vision project for detecting lanes in images. It utilizes techniques from the Udacity Self-Driving Car Nanodegree program. The project involves camera calibration, distortion correction, and lane identification. It is suitable for those learning or working on autonomous vehicle technology.

tape is a set of tasks assessing protein embeddings across different domains of protein biology. It provides data, weights, and code for running benchmarks on trained protein embeddings. The tool includes a pretraining corpus, supervised downstream tasks, pretrained language model weights, and benchmarking code.

Agentarium is an open-source framework for creating and managing simulations populated with AI agents. It provides a platform for designing interactive environments where agents can act, learn, and evolve. Agentarium allows users to create, manage, and coordinate interactions between multiple AI agents.

flow-forecast is a deep learning PyTorch library for time series forecasting, classification, and anomaly detection. Originally designed for flood forecasting, it provides state-of-the-art models like transformers, attention models, and GRUs. It offers interpretability metrics, cloud provider integration, and model serving capabilities.

SegLossOdyssey is a collection of loss functions for medical image segmentation. It provides various loss functions to improve the accuracy of image segmentation tasks. The tool is open-source and designed for researchers and practitioners in the field of medical imaging.