Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/gsurma/face_generator

DCGAN face generator 🧑.
https://github.com/gsurma/face_generator

computer-vision dcgan dcgan-tensorflow deepfake deepfakes gan gan-tensorflow jupyter-notebook notebook python

Last synced: about 1 month ago
JSON representation

DCGAN face generator 🧑.

Host: GitHub
URL: https://github.com/gsurma/face_generator
Owner: gsurma
License: mit
Created: 2019-02-11T02:16:12.000Z (almost 6 years ago)
Default Branch: master
Last Pushed: 2021-07-09T08:52:29.000Z (over 3 years ago)
Last Synced: 2023-11-07T18:57:45.566Z (about 1 year ago)
Topics: computer-vision, dcgan, dcgan-tensorflow, deepfake, deepfakes, gan, gan-tensorflow, jupyter-notebook, notebook, python
Language: Jupyter Notebook
Homepage: https://gsurma.github.io
Size: 9.33 MB
Stars: 200
Watchers: 14
Forks: 68
Open Issues: 1
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE

Awesome Lists containing this project

README

        


  



# Face Generator

Python notebook containing TensorFlow DCGAN implementation. It was trained on a [Celebrities](https://www.kaggle.com/greg115/celebrities-100k) dataset.

Check out corresponding Medium article: [Face Generator - Generating Artificial Faces with Machine Learning 🧑](https://towardsdatascience.com/face-generator-generating-artificial-faces-with-machine-learning-9e8c3d6c1ead).

Check out corresponding Kaggle kernel: [Face Generator](https://www.kaggle.com/greg115/face-generator-dcgan-celebrities).

## DCGAN

Network architecture by [Radford et al., 2015](https://arxiv.org/abs/1511.06434).



## 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**](https://gsurma.github.io)

[**GITHUB**](https://github.com/gsurma)

[**BLOG**](https://medium.com/@gsurma)