September 25, 2016

"Google has open-sourced a model for its machine-learning system, called Show and Tell, which can view an image and generate accurate and original captions."

ZDnet: The model it's released is faster to train and better at captioning images than the versions that previously helped it secure a tied first place with Microsoft Research in Microsoft's COCO 2015 image-captioning contest. By Liam Tung

'The image-captioning system is available for use with TensorFlow, Google's open machine-learning framework, and boasts a 93.9 percent accuracy rate on the ImageNet classification task, inching up from previous iterations.

'The code includes an improved vision model, allowing the image-captioning system to recognize different objects in images and hence generate better descriptions.

'An improved image model meanwhile aids the captioning system's powers of description, so that it not only identifies a dog, grass and frisbee in an image, but describes the color of grass and more contextual detail.'

"Show and Tell: image captioning open sourced in TensorFlow" by Chris Shallue here

No comments: