@@ -9,8 +9,14 @@ GAN is a generative adversarial network that we use to generate new handwritten
...
@@ -9,8 +9,14 @@ GAN is a generative adversarial network that we use to generate new handwritten
To reduce the time of execution we use Google Colab GPU;
To reduce the time of execution we use Google Colab GPU;
The MNIST dataset uses black and white images so to adapt this tutorial to the MNIST database, I changed the number of channels for 1 (in the tutorial was 3 because of RGB data used);
The MNIST dataset uses black and white images so to adapt this tutorial to the MNIST database, I changed the number of channels for 1 (in the tutorial was 3 because of RGB data used);
# cGAN tutorial.
# cGAN tutorial.
cGAN is a conditional generative adversarial network (cGAN) and in this project I trained it to identify if building facades images have generated by a model or are real;
The idea of this project is to use cGAN (a conditional generative adversarial network) to identify and juge if building facades images are real or generated by a model;
The data used is from the CMP Facade Database;
The data used is from the CMP Facade Database;
To generate the facade images, a mask, already included in the database, passes through the generator, which delivers as output a believable image.
The images were generated by a generator (with a mask from the database)
