It has been a while since we’ve posted anything on this site, but the DeepCore development team has been hard at work on the DeepCore Suite of tools. This Suite includes a series of micro-services that include tools for data set curation, chipping, scoring and inference.
We have a thick client called DeepCore Workbench that is perfectly suited to exhaustively annotate a set of images and a thin client we call DeepCore Tagging that is meant to run continuously as new data to label hits the database. Both applications add data to our sophisticated data model that the rest of the Suite interacts with.
Once training data is fully vetted, we use DeepCore Chipper and DeepCore Scoring to train our models. To run these models at scale, we leverage the service we call DeepCore Detect. This allows the end user to create their own AOI and then run that AOI on a designated schedule.
Of course, we have also been hard at work improving the DeepCore Engine as well. We’ve added support for the ONNX file format and a variety of other enhancements to include the ability to process video and radio signals. We’ve also deployed it to lower power devices for use in crunching data at the edge.
Here is a quick demo of a Youtube video that we processed using a model built from the COWC dataset.
As always, please let us know if you would like more information on DeepCore and the tools mentioned above. Enjoy!