aakashjhawar/AvatarGAN
Generate Cartoon Images using Generative Adversarial Network
Implements DC-GAN architecture with strided convolutions, batch normalization, and ReLU/LeakyReLU activations to generate cartoon avatars from the Google Cartoon Set dataset. Trains adversarial generator and discriminator networks through alternating optimization, progressively improving fake image quality over multiple epochs. Supports both local training and Google Colab execution with automatic dataset management.
No commits in the last 6 months.
Stars
65
Forks
14
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/aakashjhawar/AvatarGAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
PrasannaPulakurthi/MMD-AdversarialNAS-GAN
Enhancing GAN Performance Through Neural Architecture Search and Tensor Decomposition
gperdrizet/GANNs-with-friends
Distributed deep learning demo using DCGANNs for bootcamp students
samresume/SeriesGAN
We introduce an advanced framework that integrates the advantages of an autoencoder-generated...
nazmul-karim170/SPI-GAN
PyTorch Implementation of "SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network"
davide-abbattista/outGANfit
outGANfit - a cDCGANs-based architecture