togheppi / Cyclegan
PyTorch implementation of CycleGAN
Stars: ✭ 38
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Cyclegan
Pytorch-Image-Translation-GANs
Pytorch implementations of most popular image-translation GANs, including Pixel2Pixel, CycleGAN and StarGAN.
Stars: ✭ 106 (+178.95%)
Mutual labels: gan, image-translation, cyclegan
Pytorch Pix2pix
Pytorch implementation of pix2pix for various datasets.
Stars: ✭ 74 (+94.74%)
Mutual labels: gan, generative-adversarial-networks, image-translation
Gdwct
Official PyTorch implementation of GDWCT (CVPR 2019, oral)
Stars: ✭ 122 (+221.05%)
Mutual labels: gan, generative-adversarial-networks, image-translation
Cyclegan Tensorflow 2
CycleGAN Tensorflow 2
Stars: ✭ 330 (+768.42%)
Mutual labels: cyclegan, image-translation
Attentiongan
AttentionGAN for Unpaired Image-to-Image Translation & Multi-Domain Image-to-Image Translation
Stars: ✭ 341 (+797.37%)
Mutual labels: cyclegan, image-translation
mSRGAN-A-GAN-for-single-image-super-resolution-on-high-content-screening-microscopy-images.
Generative Adversarial Network for single image super-resolution in high content screening microscopy images
Stars: ✭ 52 (+36.84%)
Mutual labels: gan, generative-adversarial-networks
Enlightengan
[IEEE TIP'2021] "EnlightenGAN: Deep Light Enhancement without Paired Supervision" by Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang
Stars: ✭ 434 (+1042.11%)
Mutual labels: gan, generative-adversarial-networks
Tensorflow Generative Model Collections
Collection of generative models in Tensorflow
Stars: ✭ 3,785 (+9860.53%)
Mutual labels: gan, generative-adversarial-networks
Mimicry
[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.
Stars: ✭ 458 (+1105.26%)
Mutual labels: gan, generative-adversarial-networks
Cyclegan Tensorflow
Tensorflow implementation for learning an image-to-image translation without input-output pairs. https://arxiv.org/pdf/1703.10593.pdf
Stars: ✭ 676 (+1678.95%)
Mutual labels: cyclegan, image-translation
MNIST-invert-color
Invert the color of MNIST images with PyTorch
Stars: ✭ 13 (-65.79%)
Mutual labels: gan, generative-adversarial-networks
Segan
Speech Enhancement Generative Adversarial Network in TensorFlow
Stars: ✭ 661 (+1639.47%)
Mutual labels: gan, generative-adversarial-networks
Fewshot Face Translation Gan
Generative adversarial networks integrating modules from FUNIT and SPADE for face-swapping.
Stars: ✭ 705 (+1755.26%)
Mutual labels: gan, image-translation
Pycadl
Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"
Stars: ✭ 356 (+836.84%)
Mutual labels: gan, cyclegan
automatic-manga-colorization
Use keras.js and cyclegan-keras to colorize manga automatically. All computation in browser. Demo is online:
Stars: ✭ 20 (-47.37%)
Mutual labels: gan, cyclegan
Sean
SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)
Stars: ✭ 387 (+918.42%)
Mutual labels: gan, image-translation
Csmri Refinement
Code for "Adversarial and Perceptual Refinement Compressed Sensing MRI Reconstruction"
Stars: ✭ 21 (-44.74%)
Mutual labels: gan, generative-adversarial-networks
CoMoGAN
CoMoGAN: continuous model-guided image-to-image translation. CVPR 2021 oral.
Stars: ✭ 139 (+265.79%)
Mutual labels: gan, image-translation
GAN-Project-2018
GAN in Tensorflow to be run via Linux command line
Stars: ✭ 21 (-44.74%)
Mutual labels: gan, generative-adversarial-networks
CycleGAN
PyTorch implementation of CycleGAN
- Dataset can be downloaded from here.
- Loss values are plotted using Tensorboard in PyTorch.
horse2zebra dataset
- Image size: 256x256
- Number of training images: 1,334 for horse images, 1,067 for zebra images
- Number of test images: 120 for horse images, 140 for zebra images
Results
- Adam optimizer is used. Learning rate = 0.0002, batch size = 1, # of epochs = 200:
- 6 resnet blocks used for Generator.
GAN losses ( : Discriminator A / : Discriminator B : Generator A / : Generator B : Cycle loss A / : Cycle loss B ) |
Generated images (Input / Generated / Reconstructed) |
---|---|
-
Generated images using test data
Horse to Zebra
1st column: Input / 2nd column: Generated / 3rd column: ReconstructedZebra to Horse
1st column: Input / 2nd column: Generated / 3rd column: Reconstructed
apple2orange dataset
- Image size: 256x256
- Number of training images: 1,019 for apple images, 995 for orange images
- Number of test images: 266 for apple images, 248 for orange images
Results
- Adam optimizer is used. Learning rate = 0.0002, batch size = 1, # of epochs = 200:
- 9 resnet blocks used for Generator.
GAN losses ( : Discriminator A / : Discriminator B : Generator A / : Generator B : Cycle loss A / : Cycle loss B ) |
Generated images (Input / Generated / Reconstructed) |
---|---|
-
Generated images using test data
Apple to Orange
1st column: Input / 2nd column: Generated / 3rd column: ReconstructedOrange to Apple
1st column: Input / 2nd column: Generated / 3rd column: Reconstructed
References
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].