sxhxliang / Biggan Pytorch
Licence: apache-2.0
Pytorch implementation of LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS (BigGAN)
Stars: ✭ 479
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Biggan Pytorch
Tensorflow Generative Model Collections
Collection of generative models in Tensorflow
Stars: ✭ 3,785 (+690.19%)
Mutual labels: gan
Wassersteingan.tensorflow
Tensorflow implementation of Wasserstein GAN - arxiv: https://arxiv.org/abs/1701.07875
Stars: ✭ 419 (-12.53%)
Mutual labels: gan
Sean
SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)
Stars: ✭ 387 (-19.21%)
Mutual labels: gan
Simgan
Implementation of Apple's Learning from Simulated and Unsupervised Images through Adversarial Training
Stars: ✭ 406 (-15.24%)
Mutual labels: gan
Pro gan pytorch
ProGAN package implemented as an extension of PyTorch nn.Module
Stars: ✭ 425 (-11.27%)
Mutual labels: gan
Cool Fashion Papers
👔👗🕶️🎩 Cool resources about Fashion + AI! (papers, datasets, workshops, companies, ...) (constantly updating)
Stars: ✭ 464 (-3.13%)
Mutual labels: gan
Tensorflow Tutorial
Tensorflow tutorial from basic to hard, 莫烦Python 中文AI教学
Stars: ✭ 4,122 (+760.54%)
Mutual labels: gan
Generative Models
Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN
Stars: ✭ 438 (-8.56%)
Mutual labels: gan
Igan
Interactive Image Generation via Generative Adversarial Networks
Stars: ✭ 3,845 (+702.71%)
Mutual labels: gan
Simgan Captcha
Solve captcha without manually labeling a training set
Stars: ✭ 405 (-15.45%)
Mutual labels: gan
Generative Compression
TensorFlow Implementation of Generative Adversarial Networks for Extreme Learned Image Compression
Stars: ✭ 428 (-10.65%)
Mutual labels: gan
Autogan
[ICCV 2019] "AutoGAN: Neural Architecture Search for Generative Adversarial Networks" by Xinyu Gong, Shiyu Chang, Yifan Jiang and Zhangyang Wang
Stars: ✭ 388 (-19%)
Mutual labels: gan
Mimicry
[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.
Stars: ✭ 458 (-4.38%)
Mutual labels: gan
Gan Timeline
A timeline showing the development of Generative Adversarial Networks (GAN).
Stars: ✭ 379 (-20.88%)
Mutual labels: gan
Deep Learning Resources
由淺入深的深度學習資源 Collection of deep learning materials for everyone
Stars: ✭ 422 (-11.9%)
Mutual labels: gan
Tf.gans Comparison
Implementations of (theoretical) generative adversarial networks and comparison without cherry-picking
Stars: ✭ 477 (-0.42%)
Mutual labels: gan
Gantts
PyTorch implementation of GAN-based text-to-speech synthesis and voice conversion (VC)
Stars: ✭ 460 (-3.97%)
Mutual labels: gan
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 (-9.39%)
Mutual labels: gan
BigGAN-PyTorch
Pytorch implementation of LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS (BigGAN)
train imagenet
for 128*128*3 resolution
python main.py --batch_size 64 --dataset imagenet --adv_loss hinge --version biggan_imagenet --image_path /data/datasets
python main.py --batch_size 64 --dataset lsun --adv_loss hinge --version biggan_lsun --image_path /data1/datasets/lsun/lsun
python main.py --batch_size 64 --dataset lsun --adv_loss hinge --version biggan_lsun --parallel True --gpus 0,1,2,3 --use_tensorboard True
Different
- not use cross-replica BatchNorm (Ioffe & Szegedy, 2015) in G
Compatability
- CPU
- GPU
Pretrained Models
LSUN Pretrained model Download
Some methods in the paper to avoid model collapse, please see the paper and retrain your model.
Performance
- Infact, as mentioned in the paper, the model will collapse
- I use LSUN datasets to train this model maybe cause bad performance due to the class of classroom is more complex than ImageNet
Results
LSUN DATASETS(two classes): classroom and church_outdoor
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].