Simplifying AI Inference in Production with NVIDIA Triton

Originally published at: Simplifying AI Inference in Production with NVIDIA Triton | NVIDIA Developer Blog

AI machine learning is unlocking breakthrough applications in fields such as online product recommendations, image classification, chatbots, forecasting, and manufacturing quality inspection. There are two parts to AI: training and inference. Inference is the production phase of AI. The trained model and associated code are deployed in the data center or public cloud, or at…

Is it possible to use Triton server for real-time object detection and recognition from video?
Or TensorRT or something else is more suitable?

have you looked at NVIDIA DeepStream SDK? Triton & TensorRT are integrated in it and DeepStream has a variety of features for real time object detection from video streams.