Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Aaron Soellinger
Photographic Intervention in Oaxaca, MX
Photographic Intervention is a contemporary art movement with active development in Oaxaca, Mexico. In this method, artists doodle on an old print photograph to create an accessible piece of art. Photographic intervention is surprisingly profound when viewed as a fundamental critique of photography, social media and how people have used photography since its creation.
Adventures in MLOps with Github Actions, Iterative.ai, Label Studio and NBDEV
By Aaron Soellinger & Will Kunz When designing the MLOps stack for our project, we needed a solution that allowed for a high degree of customization and flexibility to evolve as our experimentation dictated. We considered large platforms that encompassed many functions, but found it limiting in some key areas. Ultimately we decided on an approach where separate specialized tools were implemented for labeling, data versioning, and continuous integration.
Machine Learning Lifecycle with MLOps: Github Actions, Label Studio, Iterative.ai and NBDEV
By: Aaron Soellinger & Will Kunz @ WallShots.co When designing the MLOps stack for our project, we needed a solution that allowed for a high degree of customization and flexibility to evolve as our experimentation dictated. We considered large platforms that encompassed many functions, but found it limiting in some key areas. Ultimately we decided on an approach where separate specialized tools were implemented for labeling, data versioning, and continuous integration.
A Comparison of Synthetic vs Human Labeled Dataset to Train a UNet Segmentation Model
By: Aaron Soellinger & Will Kunz @ WallShots.co Comparing synthetic training data to traditional training data (Image by Author) Manual labeling of data is expensive and tedious. One emergent approach to massively reduce the lift necessary to label a sufficiently large dataset for segmentation is to use synthetic data generation. In this article, we create a benchmark model using a synthetic dataset and a small traditionally labeled dataset.
Development of a Benchmark Dataset with an interface to the FastAI DataLoader using Label Studio
Sequential Illustration of the Creation of a Segmentation Mask (Image by Author) I was excited to use Label Studio because it had so much buzz in the MLOps community, and there weresome impressive visuals on their marketing webpage. The use case we’re working on is to generate detailed segmentation masks for a small number of images that can be used as a benchmark dataset as we train a model to identify the “Canvas” part of a picture frame.
Deploying a REST API to Serve the Face Profile Model
After quite a long search, I have identified several products that can be used to ease the lift required to deploy deep learning models into production. Since our end application is not clear (though we have several ideas), the best approach to productionizing this model is to deploy it as a REST service that can be maintained separately from the data science lifecycle process that produces each model, and is simple enough for each data scientist to use.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Aaron
Contact Aaron, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack