nashory / Pggan Pytorch
Licence: mit
π₯π₯ PyTorch implementation of "Progressive growing of GANs (PGGAN)" π₯π₯
Stars: β 653
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Pggan Pytorch
Cartoongan Tensorflow
Generate your own cartoon-style images with CartoonGAN (CVPR 2018), powered by TensorFlow 2.0 Alpha.
Stars: β 587 (-10.11%)
Mutual labels: gan, generative-adversarial-network, tensorboard
Textgan Pytorch
TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.
Stars: β 479 (-26.65%)
Mutual labels: gan, generative-adversarial-network
Cool Fashion Papers
πππΆοΈπ© Cool resources about Fashion + AI! (papers, datasets, workshops, companies, ...) (constantly updating)
Stars: β 464 (-28.94%)
Mutual labels: gan, generative-adversarial-network
Pix2pixhd
Synthesizing and manipulating 2048x1024 images with conditional GANs
Stars: β 5,553 (+750.38%)
Mutual labels: gan, generative-adversarial-network
Generative Compression
TensorFlow Implementation of Generative Adversarial Networks for Extreme Learned Image Compression
Stars: β 428 (-34.46%)
Mutual labels: gan, generative-adversarial-network
Generative Models
Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN
Stars: β 438 (-32.92%)
Mutual labels: gan, generative-adversarial-network
All About The Gan
All About the GANs(Generative Adversarial Networks) - Summarized lists for GAN
Stars: β 630 (-3.52%)
Mutual labels: gan, generative-adversarial-network
Fast Srgan
A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps
Stars: β 417 (-36.14%)
Mutual labels: generative-adversarial-network, tensorboard
Seqgan
A simplified PyTorch implementation of "SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient." (Yu, Lantao, et al.)
Stars: β 502 (-23.12%)
Mutual labels: gan, generative-adversarial-network
Generative Adversarial Networks
Introduction to generative adversarial networks, with code to accompany the O'Reilly tutorial on GANs
Stars: β 505 (-22.66%)
Mutual labels: gan, generative-adversarial-network
Awesome Gans
Awesome Generative Adversarial Networks with tensorflow
Stars: β 585 (-10.41%)
Mutual labels: gan, generative-adversarial-network
Deep Learning Resources
η±ζ·Ίε
₯ζ·±ηζ·±εΊ¦εΈηΏθ³ζΊ Collection of deep learning materials for everyone
Stars: β 422 (-35.38%)
Mutual labels: gan, generative-adversarial-network
Wassersteingan.tensorflow
Tensorflow implementation of Wasserstein GAN - arxiv: https://arxiv.org/abs/1701.07875
Stars: β 419 (-35.83%)
Mutual labels: gan, generative-adversarial-network
Tensorflow Tutorial
Tensorflow tutorial from basic to hard, θ«η¦Python δΈζAIζε¦
Stars: β 4,122 (+531.24%)
Mutual labels: gan, generative-adversarial-network
Ad examples
A collection of anomaly detection methods (iid/point-based, graph and time series) including active learning for anomaly detection/discovery, bayesian rule-mining, description for diversity/explanation/interpretability. Analysis of incorporating label feedback with ensemble and tree-based detectors. Includes adversarial attacks with Graph Convolutional Network.
Stars: β 641 (-1.84%)
Mutual labels: gan, generative-adversarial-network
T2f
T2F: text to face generation using Deep Learning
Stars: β 494 (-24.35%)
Mutual labels: gan, generative-adversarial-network
Simgan Captcha
Solve captcha without manually labeling a training set
Stars: β 405 (-37.98%)
Mutual labels: gan, generative-adversarial-network
Simgan
Implementation of Apple's Learning from Simulated and Unsupervised Images through Adversarial Training
Stars: β 406 (-37.83%)
Mutual labels: gan, generative-adversarial-network
Ssgan Tensorflow
A Tensorflow implementation of Semi-supervised Learning Generative Adversarial Networks (NIPS 2016: Improved Techniques for Training GANs).
Stars: β 496 (-24.04%)
Mutual labels: gan, generative-adversarial-network
Hidt
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Stars: β 513 (-21.44%)
Mutual labels: gan, generative-adversarial-network
Pytorch Implementation of "Progressive growing GAN (PGGAN)"
PyTorch implementation of PROGRESSIVE GROWING OF GANS FOR IMPROVED QUALITY, STABILITY, AND VARIATION
YOUR CONTRIBUTION IS INVALUABLE FOR THIS PROJECT :)
What's different from official paper?
- original: trans(G)-->trans(D)-->stab / my code: trans(G)-->stab-->transition(D)-->stab
- no use of NIN layer. The unnecessary layers (like low-resolution blocks) are automatically flushed out and grow.
- used torch.utils.weight_norm for to_rgb_layer of generator.
- No need to implement the the Celeb A data, Just come with your own dataset :)
How to use?
[step 1.] Prepare dataset
The author of progressive GAN released CelebA-HQ dataset, and which Nash is working on over on the branch that i forked this from. For my version just make sure that all images are the children of that folder that you declare in Config.py. Also i warn you that if you use multiple classes, they should be similar as to not end up with attrocities.
---------------------------------------------
The training data folder should look like :
<train_data_root>
|--Your Folder
|--image 1
|--image 2
|--image 3 ...
---------------------------------------------
[step 2.] Prepare environment using virtualenv
- you can easily set PyTorch (v0.3) and TensorFlow environment using virtualenv.
- CAUTION: if you have trouble installing PyTorch, install it mansually using pip. [PyTorch Install]
- For install please take your time and install all dependencies of PyTorch and also install tensorflow
$ virtualenv --python=python2.7 venv
$ . venv/bin/activate
$ pip install -r requirements.txt
$ conda install pytorch torchvision -c pytorch
[step 3.] Run training
- edit
config.pyto change parameters. (don't forget to change path to training images) - specify which gpu devices to be used, and change "n_gpu" option in
config.pyto support Multi-GPU training. - run and enjoy!
(example)
If using Single-GPU (device_id = 0):
$ vim config.py --> change "n_gpu=1"
$ CUDA_VISIBLE_DEVICES=0 python trainer.py
If using Multi-GPUs (device id = 1,3,7):
$ vim config.py --> change "n_gpu=3"
$ CUDA_VISIBLE_DEVICES=1,3,7 python trainer.py
[step 4.] Display on tensorboard (At the moment skip this part)
- you can check the results on tensorboard.
$ tensorboard --logdir repo/tensorboard --port 8888
$ <host_ip>:8888 at your browser.
[step 5.] Generate fake images using linear interpolation
CUDA_VISIBLE_DEVICES=0 python generate_interpolated.py
Experimental results
The result of higher resolution(larger than 256x256) will be updated soon.
Generated Images
Loss Curve
To-Do List (will be implemented soon)
- [ ] Support WGAN-GP loss
- [ ] training resuming functionality.
- [ ] loading CelebA-HQ dataset (for 512x512 and 1024x0124 training)
Compatability
- cuda v8.0 (if you dont have it dont worry)
- Tesla P40 (you may need more than 12GB Memory. If not, please adjust the batch_table in
dataloader.py)
Acknowledgement
Author
MinchulShin, @nashory
Contributors
DeMarcus Edwards, @Djmcflush
MakeDirtyCode, @MakeDirtyCode
Yuan Zhao, @yuanzhaoYZ
zhanpengpan, @szupzp
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].