Gene-Weaver

Will's repositories

LeafMachine2 is a modular suite of computer vision and machine learning algorithms that enables efficient identification, location, and measurement of vegetative, reproductive, and archival components from digital plant datasets.

Language:PythonGPL-3.02400

VoucherVision

Initiated by the University of Michigan Herbarium, VoucherVision harnesses the power of large language models (LLMs) to transform the transcription process of natural history specimen labels.

Language:PythonGPL-3.01400

docs-LM2

Documentation for LeafMachine2

Language:Python300

MistralMaestro

A Framework for Local Mistral (or other HF models) to Orchestrate Subagents

Language:Python600

VoucherVisionEditor

A user interface designed to efficiently edit and manage label transcriptions that are generated by VoucherVision. VoucherVision is a significant module of LeafMachine2 that leverages Large Language Models to transcribe labels attached to natural history collection specimens.

Language:PythonApache-2.0500

SLTP

Language:PythonMIT000

GreenSight

A color-based image segmentation app designed to quickly estimate biomass from common garden plots. Requires 4-monochrome flags to mark the plot corners and known plot dimensions.

Language:PythonMIT100

FieldPrism

FieldPrism curates field images by correcting image distortion, converting pixel distance to metric, and renaming files based on QR codes.

Language:PythonGPL-3.0500

LeafMachine

Deprecated - LeafMachine is a GUI that autonomously extracts leaf trait data from herbarium vouchers using CNNs, SVMs, and CV algorithms. There are two GUIs: manual version for fine-scale analyses, batch version for local files or from a list of URLs.

Language:MATLAB1300