Developer Blog: Training with Custom Pretrained Models Using the NVIDIA Transfer Learning Toolkit

AI / Deep Learning, Autonomous Machines, IVA / IoT, Development Tools & Libraries, Featured, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Apr 30 2020

This post walks you through the workflow, from downloading the TLT Docker container and AI models from NVIDIA NGC, to training and validating with your own dataset and then exporting the trained model for deployment on the edge using NVIDIA DeepStrea

Read more

Developer Blog: Speeding Up Deep Learning Inference Using TensorRT

AI / Deep Learning, Featured, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Apr 22 2020

NVIDIA TensorRT is an SDK for deep learning inference. TensorRT provides APIs and parsers to import trained models from all major deep learning frameworks.

Read more

How NVIDIA DriveWorks Makes It Easy to Perform Inference in Self-Driving Cars

Autonomous Vehicles, Automotive, Featured, TensorRT

Nadeem Mohammad, posted Apr 16 2020

On May 5, NVIDIA will host a webinar demonstrating how developers can take advantage of the NVIDIA DriveWorks SDK to perform inference for safer, more efficient self-driving.

Read more

Real-Time Object Detection in 10 Lines of Python on Jetson Nano

Autonomous Machines, Featured, Image Processing, Image Recognition, Jetson, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Jan 31 2020

To help you get up-and-running with deep learning and inference on NVIDIA’s Jetson platform, today we are releasing a new video series named Hello AI World to help you get started.

Read more

Developer Blog: How to Deploy Real-Time Text-to-Speech Applications on GPUs Using TensorRT

AI / Deep Learning, Featured, Speech & Audio Processing, TensorRT

Nadeem Mohammad, posted Jan 19 2020

In this developer blog post, we’ll walk through how to convert a PyTorch model through ONNX intermediate representation to TensorRT 7 to speed up inference in one of the parts of Conversational AI – Speech Synthesis.

Read more

TensorRT 7: Accelerate End-to-end Conversational AI with New Compiler

AI / Deep Learning, Computer Vision & Machine Vision, Featured, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Jan 18 2020

NVIDIA announces new inference speedups for automatic speech recognition (ASR), natural language processing (NLP) and text to speech (TTS) with TensorRT 7.

Read more

Inception Spotlight: Subtle Medical’s AI-based Medical Imaging Software Receives FDA Clearance

AI / Deep Learning, Computer Vision & Machine Vision, cuDNN, Healthcare & Life Sciences, Machine Learning & Artificial Intelligence, NVIDIA Inception, TensorRT

Nadeem Mohammad, posted Oct 16 2019

Subtle Medical, a member of NVIDIA’s startup accelerator, Inception, received today approval from the U.S. Food and Drug Administration to market their SubtleMR imaging processing software.

Read more

Latest Updates to NVIDIA CUDA-X Libraries

AI / Deep Learning, Top Stories, CUDA, cuDNN, Development Tools & Libraries, TensorRT

Nadeem Mohammad, posted Oct 04 2019

Learn what’s new in the latest releases of NVIDIA’s CUDA-X Libraries and NGC.

Read more

TensorFlow 2.0 with Tighter TensorRT Integration Now Available

AI / Deep Learning, Computer Vision & Machine Vision, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Oct 01 2019

To help developers build scalable ML-powered applications, Google released TensorFlow 2.0, one of the core open source libraries for training deep learning models.

Read more