Face Generator

Python notebook containing TensorFlow DCGAN implementation. It was trained on a Celebrities dataset.

Check out corresponding Medium article: Face Generator - Generating Artificial Faces with Machine Learning 🧑.

Check out corresponding Kaggle kernel: Face Generator.

DCGAN

Network architecture by Radford et al., 2015.

Training

Visualization of training with the following hyperparameteres.

DATASET_SIZE = 100000
IMAGE_SIZE = 128
NOISE_SIZE = 100
LR_D = 0.00004
LR_G = 0.0002
BATCH_SIZE = 64
EPOCHS = 60
BETA1 = 0.5
WEIGHT_INIT_STDDEV = 0.02
EPSILON = 0.00005

Results

Generated samples after 60 epochs of training.

Author

Greg (Grzegorz) Surma

PORTFOLIO

GITHUB

BLOG