Generating retro pixel game characters with Generative Adversarial Networks. Dataset "TinyHero" included.
-
Updated
May 24, 2020 - Jupyter Notebook
Generating retro pixel game characters with Generative Adversarial Networks. Dataset "TinyHero" included.
Here, we use a conditional deep convolutional generative adversarial network (cDCGAN) to inverse design across multiple classes of metasurfaces. Reference: https://onlinelibrary.wiley.com/doi/10.1002/adom.202100548
The objective of this project is to use the following Kaggle dataset (https://www.kaggle.com/datasets/soumikrakshit/anime-faces), in order to generate anime faces using a Deep Convolutional Generative Adversarial Network (DCGAN).
DCGAN model to generate metal surface defect images
Simple implement of DCGAN on CIFAR10 with one code
Repo for Implementing Research Papers & Projects related to Machine Learning
Generation Of Synthetic Images From Fashion MNIST Dataset With DCGANs In Keras.
Generating simpson faces using Deep Convolutional Generative Adversarial Networks, written in PyTorch.
Road towards diffusion models.
Repository of all notebooks used in the GANs and VAEs event.
Implementations of GANs
Generate Lego Minifigures & Faces implementing four different type of GANs in Pytorch
This is repository teaching PyTorch1.0.
A web-app based on Wasserstein Generative Adversarial Network architecture with GP that generates multiple realistic paintings, trained on 8k Albrecht Dürer's paintings, includes super-res mode.
Deep Convolutional Generative Adversarial Networks with Spectral Normalization
PyTorch implementation of various GAN architectures.
Fake Face Generation using DCGANs
Deep Convolutional GANs to generate new Pokemon
Add a description, image, and links to the dcgan-pytorch topic page so that developers can more easily learn about it.
To associate your repository with the dcgan-pytorch topic, visit your repo's landing page and select "manage topics."