Tag: TorchServe

In this post we demonstrate how to train a Twin Neural Network based on PyTorch and Fast.ai, and deploy it with TorchServe on Amazon SageMaker inference endpoint. For demonstration purposes, we build an interactive web application for users to upload images and make inferences from the trained and deployed model, based on Streamlit, which is an open source framework for data scientists to efficiently create interactive web-based data applications in pure Python.