You will use a generative adversarial network to train on the CelebA Dataset and learn to generate face images.
The top-level notebook ([login to view URL]) will guide you through the steps you need to take to implement and train a GAN. You will train two different models, the original GAN and LSGAN, which has a different loss function. The generator and discriminator network architectures you will implement are roughly based on DCGAN.
We also provide with a notebook to help with debugging called GAN_debugging.ipynb. This notebook provides a small network you can use to train on MNIST. The small network trains very quickly so you can use it to verify that your loss functions and training code are correct.
You will need to use a GPU for training your GAN. We recommend using Colab to debug, but a Google Cloud machine once your debugging is finished as you will have to run the GAN for a few hours to train fully.
Hello My friend.
My Name is Henzel, Im computer Engineer from Brazil.
I have Deep learning and python expertise and already done several codes for creating/generatin faces With GAN's during these years. I have enough knowledge to develop your project and im very hopeful to build this for you.
If you have any question or doubt about this, send me a message, im very excited to build this project for you :D
Henzel S.
Hi,
I have the worked in the field of AI for quite some time now, and have generated faces of celebrities using Generative Adversarial Networks as a research.
I have also generated medical data( with hospital's consent) with a good accuracy.