AutoML is an Azure Machine Learning feature, that empowers both professional and citizen data scientists to build machine learning models rapidly. Since its launch, AutoML has helped accelerate model building for essential machine learning tasks like Classification, Regression and Time-series Forecasting.
There is as well some Computer Vision algorithms available with AutoML for Images.
You can find here some Python notebooks templates you can use for your computer vision projects with Azure ML:
-
Image Classification
Image classification demo notebook -
Object Detection
Object detection demo notebook (part 1)
Object detection demo notebook (part 2) -
Instance Segmentation
Instance segmentation demo notebook -
Calling deployed model as an Azure ML endpoint
Instanced segmentation model (version 1 with connection to the Azure ML workspace)
Instanced segmentation model (version 2 with no connection to the Azure ML workspace)
- What is AutoML for Images? https://docs.microsoft.com/en-us/azure/machine-learning/concept-automated-ml#computer-vision-preview
- Algorithms https://docs.microsoft.com/en-us/azure/machine-learning/how-to-auto-train-image-models#supported-model-algorithms
- Tutorials https://learn.microsoft.com/en-us/azure/machine-learning/tutorial-auto-train-image-models?tabs=cli
- ONNX https://docs.microsoft.com/en-us/azure/machine-learning/how-to-inference-onnx-automl-image-models?tabs=multi-class
- How to use AutoML for Images? https://docs.microsoft.com/en-us/azure/machine-learning/how-to-use-automl-small-object-detect https://learn.microsoft.com/en-us/azure/machine-learning/how-to-auto-train-image-models?tabs=cli
- About Azure ML https://azure.microsoft.com/en-us/services/machine-learning/
10-Feb-2023 Serge Retkowsky | [email protected] | https://www.linkedin.com/in/serger/