Once the data is loaded, Snark helps to apply various transformations on the images as if they are in a local machine. The tool helps to build data pipelines that can be effortlessly scaled to a cluster of machines.
Transformations include downscaling, cropping, shuffling, sampling and all other numpy supported functions on aerial images. One can easily compute NDVI by applying simple subtraction and division on a huge array.
Data pipelines can turn raw data into datasets that you can train machine learning and deep learning models. The dataset generations can achieve near-real-time computation such that training can start instantly.
The tool helps to train aerial image classification tasks such as identifying the crop type or image segmentation for example for identifying roof boundaries.
Snark will connect to your current storage, ingest the data, and show you the results within days.
Our team of machine learning experts will help you with data pre-processing, model selection, feature engineering support as much or as little as you need.
Enterprise-grade cloud computing optimized down to cents. Leverages the most cost-efficient resources such as spot instances.