Frame by frame identification and tracking in endoscopy
Technical Walkthrough 0

AI in Endoscopy: Improving Detection Rates and Visibility with Real-Time Sensing

Clinical applications for AI are improving digital surgery, helping to reduce errors, provide consistency, and enable surgeon augmentations that were previously... 4 MIN READ
Technical Walkthrough 2

Beating SOTA Inference Performance on NVIDIA GPUs with GPUNet

Crafted by AI for AI, GPUNet is a class of convolutional neural networks designed to maximize the performance of NVIDIA GPUs using NVIDIA TensorRT. Built using... 6 MIN READ
Technical Walkthrough 0

Getting Started with the Deep Learning Accelerator on NVIDIA Jetson Orin

If you’re an active Jetson developer, you know that one of the key benefits of NVIDIA Jetson is that it combines a CPU and GPU into a single module, giving... 3 MIN READ
Technical Walkthrough 3

Optimizing and Serving Models with NVIDIA TensorRT and NVIDIA Triton

Imagine that you have trained your model with PyTorch, TensorFlow, or the framework of your choice, are satisfied with its accuracy, and are considering... 11 MIN READ
Technical Walkthrough 4

Exploring NVIDIA TensorRT Engines with TREx

The primary function of NVIDIA TensorRT is the acceleration of deep-learning inference, achieved by processing a network definition and converting it into an... 16 MIN READ
Technical Walkthrough 1

Accelerating Quantized Networks with the NVIDIA QAT Toolkit for TensorFlow and NVIDIA TensorRT

We’re excited to announce the NVIDIA Quantization-Aware Training (QAT) Toolkit for TensorFlow 2 with the goal of accelerating the quantized networks with... 9 MIN READ