Conditional Face Generation

Generation of faces with specific attributes using Generative Adversarial Networks (GANs) on CelebA dataset

Model

Conditional DCGAN. Labels vector concatenated in the discriminator by means of vectorization. More details can be found in the file cGAN.ipynb

Results

The model achieves a State of the Art FID score of 11.7

• Unconditional generation

  

• Female, Young, Attractive, Brown_Hair, Bangs, Heavy_Makeup

  

• Male, Old, Bald, Arched_Eyebrows, Bushy_Eyebrows, Pale_Skin, No_Beard

  

• Male, Attractive, Brown_Hair, Straight_Hair, Smiling, Eyeglasses, Mustache

  

• Female, Young, Attractive, Blond_Hair, Smiling, Eyeglasses