Neural Network to Create Photos From Sketches

The developers can create apps with a Python written neural network called iSketchNFill, code of which is available at GitHub
30 September 2019   318

A real-time neural network turns sketches into photographs. A group of American and British experts led by a developer from Adobe Research created such a system called iSketchNFill. The algorithm consists of two parts. One draws a sketch, the second makes a realistic photo out of the finished picture.

Based on the neural network, the developers created an application for Linux and macOS. Its code is available at GitHub.

The application has two windows. In the first, the user schematically draws an object, and in the second, he creates a neural network in real time. Before you start drawing, you need to select a specific object from the list. The neural network can handle sketches of faces, cars, bicycles, as well as some fruits and berries.

TensorFlow 2.0 to be Released

New major release of the machine learning platform brought a lot of updates and changes, some stuff even got cut
01 October 2019   197

A significant release of the TensorFlow 2.0 machine learning platform is presented, which provides ready-made implementations of various deep machine learning algorithms, a simple programming interface for building models in Python, and a low-level interface for C ++ that allows you to control the construction and execution of computational graphs. The system code is written in C ++ and Python and is distributed under the Apache license.

The platform was originally developed by the Google Brain team and is used in Google services for speech recognition, facial recognition in photographs, determining the similarity of images, filtering spam in Gmail, selecting news in Google News and organizing the translation taking into account the meaning. Distributed machine learning systems can be created on standard equipment, thanks to the built-in support in TensorFlow for spreading computing to multiple CPUs or GPUs.

TensorFlow provides a library of off-the-shelf numerical computation algorithms implemented through data flow graphs. The nodes in such graphs implement mathematical operations or entry / exit points, while the edges of the graph represent multidimensional data arrays (tensors) that flow between the nodes. The nodes can be assigned to computing devices and run asynchronously, simultaneously processing all the suitable tensors at the same time, which allows you to organize the simultaneous operation of nodes in the neural network by analogy with the simultaneous activation of neurons in the brain.

Get more info about the update at official website.