Oracle to Open GraphPipe Source Code

GraphPipe is a tool that simplifies the maintenance of machine learning models
17 August 2018   796

Oracle has opened the source code of the GraphPipe tool to simplify the maintenance of machine learning models. It supports projects based on the TensorFlow, MXNet, Caffe2 and PyTorch libraries. They are intended for use in IoT-devices, custom web-services and corporate AI-platforms.

The tool eliminates the need for developers to create custom APIs. Also, it eliminates confusion when using multiple frameworks and prevents memory copying during deserialization. The developers hope that GraphPipe will become a standard tool for deploying models.

GraphPipe is free and available on GitHub. It consists of open source tools designed to work with artificial intelligence. For example, the TensorFlow framework and the Open Neural Network Exchange (ONNX) project for creating portable neural networks are among them.

In September 2017, Microsoft introduced own tools for operating with machine learning. At the same time, the company released utilities for using Visual Studio Code when creating models based on the CNTK and Keras frameworks.

Neural Network to Create Landscapes from Sketches

Nvidia created GauGAN model that uses generative-competitive neural networks to process segmented images and create beautiful landscapes from peoples' sketches
20 March 2019   127

At the GTC 2019 conference, NVIDIA presented a demo version of the GauGAN neural network, which can turn sketchy drawings into photorealistic images.

The GauGAN model, named after the famous artist Paul Gauguin, uses generative-competitive neural networks to process segmented images. The generator creates an image and transfers it to the discriminator trained in real photographs. He in turn pixel-by-pixel tells the generator what to fix and where.

Simply put, the principle of the neural network is similar to the coloring of the coloring, but instead of children's drawings, it produces beautiful landscapes. Its creators emphasize that it does not just glue pieces of images, but generates unique ones, like a real artist.

Among other things, the neural network is able to imitate the styles of various artists and change the times of the day and year in the image. It also generates realistic reflections on water surfaces, such as ponds and rivers.

So far, GauGAN is configured to work with landscapes, but the neural network architecture allows us to train it to create urban images as well. The source text of the report in PDF is available here.

GauGAN can be useful to both architects and city planners, and landscape designers with game developers. An AI that understands what the real world looks like will simplify the implementation of their ideas and help you quickly change them. Soon the neural network will be available on the AI ​​Playground.