Original reference DCGAN in an unmaintained Theano-era codebase; choose only to reproduce the original paper experiments.
Deep Convolutional Generative Adversarial Networks
- 3.5k
- Python
- MIT
Generative adversarial networks / image synthesis
A TensorFlow implementation of Deep Convolutional Generative Adversarial Networks (DCGAN) for training on image datasets.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Original reference DCGAN in an unmaintained Theano-era codebase; choose only to reproduce the original paper experiments.
Deep Convolutional Generative Adversarial Networks
DCGAN implemented in legacy Keras 1.x, not maintained; pick only for old Keras-only projects.
Keras implementation of Deep Convolutional Generative Adversarial Networks
DCGAN in the discontinued Chainer framework; choose it only if you are locked into Chainer.
Chainer implementation of Deep Convolutional Generative Adversarial Network
PyTorch DCGAN-style model already configured for anime face generation; choose when that domain is sufficient.
A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing.
These projects were analysed and named DCGAN-tensorflow among their alternatives. The relationship is not symmetric — how DCGAN-tensorflow rates them is a separate judgement, made when DCGAN-tensorflow is analysed in its own right.
calls DCGAN-tensorflow “specific DCGAN in TensorFlow, if you only need that model”
PyTorch implementations of Generative Adversarial Networks.
calls DCGAN-tensorflow “Choose for a minimal DCGAN implementation in TensorFlow as an educational baseline.”
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
calls DCGAN-tensorflow “use when you need the canonical DCGAN TensorFlow implementation as a standalone example.”
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.