Amazon SageMaker adds new APIs for JumpStart models
Amazon SageMaker JumpStart helps you quickly and easily solve your machine learning problems with one-click access to 322 popular model collections from TensorFlow Hub, PyTorch Hub, Hugging Face and Gluon CV (also known as “model zoos”), and to 17 end-to-end solutions that solve common business problems such as demand forecasting, fraud detection and document understanding.
Amazon SageMaker JumpStart helps you quickly and easily solve your machine learning problems with one-click access to 322 popular model collections from TensorFlow Hub, PyTorch Hub, Hugging Face and Gluon CV (also known as “model zoos”), and to 17 end-to-end solutions that solve common business problems such as demand forecasting, fraud detection and document understanding.
Starting today, customers can use all the 322 popular ML models from SageMaker JumpStart through published APIs in SageMaker Python SDK. Through using these APIs in Python programs, customers can automate the deployment and training of these models for production use. These APIs cover a wide range of machine learning tasks including image classification, object detection, semantic segmentation, instance segmentation, image embedding, text classification, sentence pair classification, question answering, text embedding, text summarization, text generation, machine translation, tabular classification and tabular regression. Please view our documentation for details on how to use these APIs.
Amazon SageMaker JumpStart is available in all regions where Amazon SageMaker Studio is available. To get started with these new models on SageMaker JumpStart, refer to the documentation.