Meson 0.50 to be Available

The key development goal of Meson is to ensure a high speed of the assembly process, combined with convenience and ease of use
11 March 2019   393

The release of the Meson 0.50 build system is introduced, which is used to build projects such as X.Org Server, Mesa, Lighttpd, systemd, GStreamer, Wayland, GNOME and GTK +. Meson code is written in Python and comes under the Apache 2.0 license.

The key development goal of Meson is to ensure a high speed of the assembly process, combined with convenience and ease of use. Instead of the make utility, the Ninja toolkit is used in the default build, but other backends can also be used, such as xcode and VisualStudio. A multi-platform dependency handler is built into the system, allowing you to use Meson to build packages for distributions. The build rules are set in a simplified domain-specific language, are well readable and understandable to the user (according to the authors' idea, the developer should spend the least amount of time writing the rules).

Cross-compilation and build on Linux, macOS and Windows using GCC, Clang, Visual Studio and other compilers are supported. Building projects in various programming languages is possible, including C, C ++, Fortran, Java and Rust. An incremental build mode is supported, in which only components directly related to changes made since the last build are reassembled. Meson can be used to form repeatable assemblies, in which the launch of an assembly in different environments leads to the generation of completely identical executable files.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   854

NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.

Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.

Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.

To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.