Software Engineering
<- Return to all blogs
-
Transfer Learning from RGB to Multi-band Imagery
We used transfer learning to teach a model to take advantage of multi-band imagery without discarding the original RGB pre-training. This resulted in significant performance improvement.
-
Transfer Learning from RGB to Multi-band Imagery
We used transfer learning to teach a model to take advantage of multi-band imagery without discarding the original RGB pre-training. This resulted in significant performance improvement.
-
Using the Dedupe Machine Learning Library for Cleaning and Matching Data
To deal with issues of apparel facility list data quality and scale quickly and efficiently we need a machine learning tool that can capture the knowledge of domain experts, find commonalities in jumbled text, and confidently compare large lists without the need to compare each individual entry.
-
Rising From The Ashes, Untangling the Mysteries of DevOps
There are many books that have influenced me as a software engineer. From the computer science textbooks I used in college, to the animal covered books from OโReilly I used to pick up new languages and tools, to the Clean Code books from Uncle Bob Martin that helped shape the way I approach software development. However,…
-
Connecting Data and People with the Open Apparel Registry
Since its launch on March 28, the Open Apparel Registry (OAR) has grown to include over 18,300 facilities in 92 countries. Weโve already heard of a few fascinating use cases where data from the OAR contributed to decision making by brands and facilities.
-
Using Noisy Labels to Train Deep Learning Models on Satellite Imagery
How do noisy labels affect the accuracy of a deep learning model? We added different amounts of noise to the SpaceNet Vegas buildings dataset and trained some models to find out.
-
An Introduction to Machine Learning Accuracy Metrics
How accurate of a machine learning model can you make? It depends on how we decide to define “accurate”.
-
E84 @ 2019 ESIP Summer Meeting
We’re passionate about Earth Science Data and helping to solve the challenges in that field. At this year’s ESIP Summer Meeting, we have five E84 team members speaking and moderating across six different sessions, with an additional four of us out there to chat and support the event. Here’s where you can find us if…
-
Cloud-native Apps Force Developers to Put Security First
Data stored in the cloud is an attractive target for hackers. High profile breaches like the recent exposure of images of license plates at a U.S. port of entry have become commonplace. These events justifiably alarm consumers. Every incident cements distrust toward the tech industry, causing technology users to demand better security from software creators.…
-
Introducing WMS and WCS Support for GeoTrellis and Raster Foundry
Raster Foundry and GeoTrellis now support WMS and WCS standards, enabling streamlined workflows that utilize multiple data sources.
-
MUB Monitor: Helping Water Utilities Track and Respond to Upstream Threats
In partnership with Downstream Strategies, we created MUB Monitor – a comprehensive GIS-based tool that helps water professionals track spills, assess watershed threats, and make informed decisions.
