The Imagery AI toolset contains tools that apply object detection and pixel classification deep learning algorithms to imagery data.
Training deep learning models has traditionally been a complex process that required specialized knowledge of different types of model architecture and how their parameters (known as hyperparameters) could be fine-tuned to get the best results. This is an iterative process that requires several experiments before the most accurate model and its appropriate hyperparameters can be identified. The Train Using AutoDL tool automates this process without having to write code. The tool provides visibility into the performance and hyperparameters of the trained models.
Tools in the Imagery AI toolset
| Tool | Description |
|---|---|
|
Runs one or more pretrained deep learning models on an input raster to extract features and automate the postprocessing of the inferenced outputs. | |
Trains a deep learning model by building training pipelines and automating much of the training process. This includes data augmentation, model selection, hyperparameter tuning, and batch size deduction. Its outputs include performance metrics of the best model on the training data, as well as the trained deep learning model package (.dlpk file) that can be used as input for the Extract Features Using AI Models tool to predict on a new imagery. |