hiwonjoon / Cycle Gan Tf
Licence: mit
Reimplementation of cycle-gan(https://arxiv.org/pdf/1703.10593.pdf) with improved w-gan(https://arxiv.org/abs/1704.00028) loss in tensorflow.
Stars: ✭ 74
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Cycle Gan Tf
Keras Gan
Keras implementations of Generative Adversarial Networks.
Stars: ✭ 8,494 (+11378.38%)
Mutual labels: gan
Pix2pix
Image-to-image translation with conditional adversarial nets
Stars: ✭ 8,765 (+11744.59%)
Mutual labels: gan
Man
Multinomial Adversarial Networks for Multi-Domain Text Classification (NAACL 2018)
Stars: ✭ 72 (-2.7%)
Mutual labels: gan
Cyclegan Qp
Official PyTorch implementation of "Artist Style Transfer Via Quadratic Potential"
Stars: ✭ 59 (-20.27%)
Mutual labels: gan
Esrgan Tf2
ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks, published in ECCV 2018) implemented in Tensorflow 2.0+. This is an unofficial implementation. With Colab.
Stars: ✭ 61 (-17.57%)
Mutual labels: gan
Sequentialdata Gan
Tensorflow Implementation of GAN modeling for sequential data
Stars: ✭ 69 (-6.76%)
Mutual labels: gan
Acgan Pytorch
Pytorch implementation of Conditional Image Synthesis with Auxiliary Classifier GANs
Stars: ✭ 57 (-22.97%)
Mutual labels: gan
Frechet Inception Distance
CPU/GPU/TPU implementation of the Fréchet Inception Distance
Stars: ✭ 66 (-10.81%)
Mutual labels: gan
Geneva
Code to train and evaluate the GeNeVA-GAN model for the GeNeVA task proposed in our ICCV 2019 paper "Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction"
Stars: ✭ 71 (-4.05%)
Mutual labels: gan
Deblurgan Tf
Unofficial tensorflow (tf) implementation of DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
Stars: ✭ 60 (-18.92%)
Mutual labels: gan
Colorizer
Add colors to black and white images with neural networks (GANs).
Stars: ✭ 69 (-6.76%)
Mutual labels: gan
Hypergan
Composable GAN framework with api and user interface
Stars: ✭ 1,104 (+1391.89%)
Mutual labels: gan
Cyclegan Tensorflow
An implementation of CycleGan using TensorFlow
Stars: ✭ 1,096 (+1381.08%)
Mutual labels: gan
Pacgan
[NeurIPS 2018] [JSAIT] PacGAN: The power of two samples in generative adversarial networks
Stars: ✭ 67 (-9.46%)
Mutual labels: gan
Pytorch Pix2pix
Pytorch implementation of pix2pix for various datasets.
Stars: ✭ 74 (+0%)
Mutual labels: gan
Imagedeblurring
A Keras implementation of image deblurring based on ICCV 2017 paper "Deep Generative Filter for motion deblurring"
Stars: ✭ 72 (-2.7%)
Mutual labels: gan
Dcgan Tensorflow
A Tensorflow implementation of Deep Convolutional Generative Adversarial Networks trained on Fashion-MNIST, CIFAR-10, etc.
Stars: ✭ 70 (-5.41%)
Mutual labels: gan
Cycle-GAN-TF
Reimplementation of cycle-gan with improved w-gan loss in tensorflow.
Prerequisites
- Tensorflow v1.0
Training Result
- Training is done with nVidia Titan X Pascal GPU.
- aerial maps <-> maps
- A(aerial map) -> B(map) -> A
- B -> A -> B
- A(aerial map) -> B(map) -> A
Result on test sets
-
Each model trained 20000 steps(20000*8/1000 ~= about 160 epochs).
-
aerial maps <-> maps
-
horse <-> zebra
-
apple <-> orange
Training
Download dataset
./download_dataset.sh [specify a dataset you want]
Run code
Before running the code, change the paths and hyper-parameters as desired in the code.
python main.py
Using pretrained model & inference
Before running the code, change the paths as desired in the code.
python inference.py
Notes & Acknowledgement
- The code for download dataset was copied from here.
- Network architecture might slightly different from the original paper's one.
- For instance, different D network (actually, C network in the Wasserstein gan) is used.
- Tensorflow does not support reflection padding for conv(and decov) layer, so some artifacts can be seen.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].