Isaac Corley
San Antonio, Texas, United States
Summary
🤩
RockstarIsaac Corley is an experienced ML engineer and data scientist with nine years focused on geospatial AI, computer vision, and foundation models, currently based in San Antonio. Pursuing an EE PhD at UTSA, he bridges academic rigor with practical open-source impact as a maintainer on TorchGeo and a contributor to influential projects like Google's Flax. His contributions span dataset engineering, model-compatible image handling (t,c,h,w refactor), and implementing/core-testing neural components such as PReLU, reflecting deep attention to correctness and usability. Comfortable across research and production code, he brings a rare combination of geospatial domain expertise and low-level ML library development.
9 years of coding experience
Github Skills (14)
neural-network10
computer-vision10
pytorch10
machine-learning10
deep-learning10
pytorch-geometric10
jax10
geospatial10
sens10
python10
flax10
datasets10
testing10
documentation8
Programming languages (5)
Github contributions (5)
microsoft/torchgeo
Sep 2021 - Dec 2022
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Role in this project:
Data Scientist & ML Engineer
Data Scientist & ML EngineerContributions:1 release, 542 reviews, 86 commits in 1 year 3 months
Contributions summary:Isaac primarily contributed to the development of the `TorchGeo` library, specifically focusing on the implementation and testing of new datasets. Their work included adding the `LEVIRCDPlus` dataset, with associated tests and documentation updates. Furthermore, the user refactored the image output to match the shape (t, c, h, w), demonstrating an understanding of image data handling and model compatibility within the context of geospatial data analysis and deep learning.
pytorchsamplersgeospatialdeep-learningearth-observation
google/flax
Sep 2021 - Oct 2021
Flax is a neural network library for JAX that is designed for flexibility.
Role in this project:ML Engineer
ML EngineerContributions:6 commits, 1 PR, 4 comments in 1 month
Contributions summary:Isaac contributed to the Flax library by implementing and testing a PReLU (Parametric Rectified Linear Unit) activation function. They added the PReLU implementation, created tests to validate its functionality within the Flax framework, and integrated the activation function into the library's documentation. The user's work involved modifications to core neural network modules and related documentation updates.
deep-learningneural-networksneural-networkflaxjax
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.