Recursive ML at the Edge: Case Study - Training a Bird Species Identifier
- 0 Collaborators
Using an existing image recognition model we built a secondary seed library to extend the classifier to make a more specific model. ...learn more
Overview / Usage
This case study utilizes an existing MXNet model for simple object recognition to build a library of seed images to train a model for more specific species identification in birds. This methodology easily adapts to any subclassifications scenario and provides automation for model training while collecting field data at the edge using AWS DeepLens ML platform with Greengrass and Sagemaker.