Data Science

New GPU Optimized Models and Notebooks Available from TensorFlow Hub, Google AI Hub, Google Colab

This week at TensorFlow World, Google announced community contributions to TensorFlow hub, a machine learning model library. NVIDIA was a key participant, providing models and notebooks to TensorFlow Hub along with new contributions to Google AI Hub and Google Colab containing GPU optimizations from NVIDIA CUDA-X AI libraries.

UNet Models and Notebooks for Industrial Quality Inspection

The UNet model is a convolutional auto-encoder for 2D image segmentation used in industrial quality inspection.

NVIDIA contributed 10 variations of UNet to TensorFlow Hub with notebooks to try, each specializing in detecting different defects (eg: scratches, spots, etc.). NVIDIA also published a UNet notebook to the Google AI Hub with TensorFlow-TensorRT integration for optimized inference deployment.

Available from: TensorFlow Hub | Google AI Hub

BERT Question Answering Inference with Mixed Precision

Bidirectional Embedding Representations from Transformers (BERT), is a method of pre-training language representations which obtains state-of-the-art results on a wide array of Natural Language Processing (NLP) tasks. 

This notebook walks through how to perform optimized inference for QA tasks with BERT-Large using mixed precision on Tensor Core GPUs.

Available from: Google AI Hub | Google Colab 

Additional contributions and collaborations to come from NVIDIA and Google.

These models and more are also available to try from NGC and NVIDIA Deep Learning Examples on GitHub.

Discuss (0)