Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   2396

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.

Data Natives 2019 After Movie Released

Check the videoreport from one of the largest tech event of the year
19 December 2019   660

As you may remember, Data Natives organizes events in 50 largest tech capitals all over the globe. And the biggest annual conference is held in the home of the Data Natives - Berlin.

3500+ programmers, startupers, tech fans and professionals from the world of the newest technology visited the event this year.

Data Natives 2019 was a great success - during the 7 days of 25+ satellite events, 8,5h of workshops, 8h of inspiring keynotes, 10h of panels on five stages and a 48 hours-long hackathon, over 3500 data enthusiasts, professionals, founders and experts met, engaged and learned from 182+ speakers. We were sold out 2 days prior to the event and reached 8,9M impressions on DN19 hashtag - thank you for your support.

DN Team in Comment to Hype.Codes

We've visited the event and made a report. Check it out!

And now the time for the another update has come. Check the after movie of the event to feel it's atmosphare and energy. The report will give you the chance to see whole thing by yourself if missed the event.

Interested? Don't hesitate, and...


Holiday special ends in 17 days!