https://github.com/diegoalejogm/gans
Generative Adversarial Networks implemented in PyTorch and Tensorflow
https://github.com/diegoalejogm/gans
cyclegan dcgans gans gans-collections paper-implementations pytorch tensorflow
Last synced: 5 months ago
JSON representation
Generative Adversarial Networks implemented in PyTorch and Tensorflow
- Host: GitHub
- URL: https://github.com/diegoalejogm/gans
- Owner: diegoalejogm
- License: mit
- Created: 2017-12-22T16:15:37.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2022-12-08T09:35:50.000Z (over 3 years ago)
- Last Synced: 2024-08-08T23:19:06.824Z (almost 2 years ago)
- Topics: cyclegan, dcgans, gans, gans-collections, paper-implementations, pytorch, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 25.8 MB
- Stars: 826
- Watchers: 28
- Forks: 353
- Open Issues: 19
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# gans: Generative Adversarial Networks
Multiple Generative Adversarial Networks (GANs) implemented in PyTorch and Tensorflow.
[Check out this blog post](https://medium.com/ai-society/gans-from-scratch-1-a-deep-introduction-with-code-in-pytorch-and-tensorflow-cb03cdcdba0f) for an introduction to Generative Networks.
## Vanilla GANs
Vanilla GANs found in this project were developed based on the original paper [Generative Adversarial Networks](https://arxiv.org/abs/1406.2661) by Goodfellow et al.
These are trained on the [MNIST dataset](http://yann.lecun.com/exdb/mnist/), and learn to create hand-written digit images using a 1-Dimensional vector representation for 2D input images.
- [PyTorch Notebook](https://github.com/diegoalejogm/gans/blob/master/1.%20Vanilla%20GAN%20PyTorch.ipynb)
- [TensorFlow Notebook](https://github.com/diegoalejogm/gans/blob/master/1.%20Vanilla%20GAN%20TensorFlow.ipynb)
__MNIST-like generated images before & after training.__
## DCGANs
Deep Convolutional Generative Adversarial Networks (DCGANs) in this repository were developed based on the original paper [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://arxiv.org/abs/1511.06434) by Radford et al.
These are trained on the [CIFAR10](https://www.cs.toronto.edu/~kriz/cifar.html) and the [MNIST](http://yann.lecun.com/exdb/mnist/) datasets. They use 3 dimensional representations for images (length x height x colors) directly for training.
- [TensorFlow CIFAR10 Notebook](https://github.com/diegoalejogm/gans/blob/master/2.%20DC-GAN%20TensorFlow.ipynb)
- [PyTorch CIFAR10 Notebook](https://github.com/diegoalejogm/gans/blob/master/2.%20DC-GAN%20PyTorch.ipynb)
- [PyTorch MNIST Notebook](https://github.com/diegoalejogm/gans/blob/master/2.%20DC-GAN%20PyTorch-MNIST.ipynb)
__CIFAR-like generated images before & after training.__