NVIDIA TensorRT Inference Server Boosts Deep Learning Inference

Artificial Intelligence, Cloud Services, Containers, Deep Learning, Featured, GPU, machine learning and AI, NGC, TensorRT, TensorRT Inference Server

Nadeem Mohammad, posted Sep 12 2018

You’ve built, trained, tweaked and tuned your model. You finally create a TensorRT, TensorFlow or ONNX model that meets your requirements. Now you need an inference solution, deployable to a datacenter or to the cloud.

Read more

Video: Introduction to Recurrent Neural Networks in TensorRT

Artificial Intelligence, Deep Learning, machine learning and AI, RNN, TensorRT

Nadeem Mohammad, posted Sep 10 2018

NVIDIA TensorRT™ is a high-performance deep learning inference optimizer and runtime that delivers low latency and high-throughput.

Read more

Accelerating Recommendation System Inference Performance with TensorRT

Artificial Intelligence, machine learning and AI, MovieLens, TensorRT, Tutorial, video

Nadeem Mohammad, posted Sep 05 2018

NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications.

Read more

Accelerate Video Analytics Development with DeepStream 2.0

Artificial Intelligence, Smart Cities, Accelerated Computing, DeepStream, Development Tools and Libraries, machine learning and AI, machine vision, Video Processing

Nadeem Mohammad, posted Aug 28 2018

The sheer scale of the smart city boggles the mind. Tens of billions of sensors will be deployed worldwide, used to make every street, highway, park, airport, parking lot, and building more efficient.

Read more

Mixed-Precision ResNet-50 Using Tensor Cores with TensorFlow

Artificial Intelligence, Deep Learning, machine learning and AI, NGC, resnet-50, Tensor Core, TensorFlow, video

Nadeem Mohammad, posted Aug 28 2018

Mixed-Precision combines different numerical precisions in a computational method. Using precision lower than FP32 reduces memory usage, allowing deployment of larger neural networks.

Read more