The script will transform input.png to output.png. Put these file in a dir named: checkpoints. To run the script you need the pythorch models: the large files (700MB) that are on the net ( cm.lib, mm.lib, mn.lib). The nature and meaning of these transformations are not very important, and have been discovered after numerous trial and error attempts.Ĭonsidering these additional transformations, and including the final insertion of watermarks, the phases of the algorithm are the following:īefore launch the script install these packages in your Python3 environment: To optimize the result, simple computer vision transformations are performed before each GAN phase, using OpenCV. Although it is possible to use some automations, the creation of these datasets still require great and repetitive manual effort. Working on stylized and abstract graphic fields the construction of these datasets becomes a mere problem of hours working on photoshop to mask photos and apply geometric elements. Web scrapers can download thousands of images from the web, dressed and nude, and through photoshop you can apply the appropriate masks and details to build the dataset that solve a particular sub problem. This approach makes the construction of the sub-datasets accessible and feasible. Generation of a abstract representation of anatomical attributes.Generation of a mask that selects clothes.Instead of relying on a single network, we divided the problem into 3 simpler sub-problems: We overcome the problem using a divide-et-impera approach. A database in which a person appears both naked and dressed, in the same position, is extremely difficult to achieve, if not impossible. Paired datasets get better results and are the only choice if you want to get photorealistic results, but there are cases in which these datasets do not exist and they are impossible to create. If you are interested in the details of the network you can study this amazing project provided by NVIDIA.Ī GAN network can be trained using both paired and unpaired dataset. How DeepNude works?ĭeepNude uses a slightly modified version of the pix2pixHD GAN architecture. This repo contains only the core algorithm, not the user interface. We are sure that github's community can take the best from this controversial algorithm, and inspire other and better creative tools. The purpose of this repo is only to add technical information about the algorithm and is aimed at specialists and programmers, who have asked us to share the technical aspects of this creative tool.ĭeepNude uses an interesting method to solve a typical AI problem, so it could be useful for researchers and developers working in other fields such as fashion, cinema and visual effects. So it no longer makes sense to hide the source code. Two days after the launch, the reverse engineering of the app was already on github. The original DeepNude Software and all its safety measures have been violated and exposed by hackers.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |