Both live-mode operation and hard disk installation are both supported in GhostBSD
15 April 2019
Desktop-oriented GhostBSD 19.04 was released, built on the basis of TrueOS and offering the user environment MATE. By default, GhostBSD uses the OpenRC initialization system and the ZFS file system. Both live-mode operation and hard disk installation are supported (the own ginstall installer written in Python is used). Boot images are generated for the architecture amd64 (2.7 GB).
In the new version:
The codebase has been upgraded to the FreeBSD 13.0-CURRENT experimental branch;
The installer adds support for ZFS file system on partitions with MBR;
To improve UFS installation support, remove the default ZFS settings for TrueOS;
Instead of slim, the Lightdm session manager is involved;
Gksu removed from shipment;
Added "boot_mute" mode to boot without displaying the log on the screen;
A block of settings for the rEFInd boot manager has been added to the installer.
SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019
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.