AI Rank
中文
← Open Source
christiancosgrove

pytorch-spectral-normalization-gan

Paper by Miyato et al. https://openreview.net/forum. id=B1QRgziT-.

Model DevelopmentArchitecturePython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
677
Stars
109
Forks
+0
This week
1
Contributors
Created 2017-12-01 · Updated 2026-09-16 · #15128 today
Top developers
christiancosgrove

christiancosgrove/pytorch-spectral-normalization-gan is ranked 15,128 with 677 stars.

Same-category comparison

christiancosgrove/pytorch-spectral-normalization-gan is ranked 15,128 among these 8 peers; google/yggdrasil-decision-forests is ranked 15,129.

Same-category comparison
NameRankMetrics
OpenDriveLab/OpenLane-V215,105
Language:
Jupyter Notebook
Stars:
678
Forks:
78
Description:
[NeurIPS 2023 Track Datasets and Benchmarks] OpenLane-V2: The First Perception and Reasoning Benchmark for Road Driving.
skumra/robotic-grasping15,120
Language:
Python
Stars:
678
Forks:
151
Description:
Antipodal Robotic Grasping using GR-ConvNet. IROS 2020.
EmuKit/emukit15,122
Language:
Python
Stars:
677
Forks:
135
Description:
A Python-based toolbox of various methods in decision making, uncertainty quantification and statistical emulation: multi-fidelity, experimental design, Bayesian optimisation, Bayesian quadrature, etc.
TalkingData/Fregata15,126
Language:
Scala
Stars:
677
Forks:
182
Description:
A light weight, super fast, large scale machine learning library on spark .
google/yggdrasil-decision-forests15,129
Language:
C++
Stars:
677
Forks:
85
Description:
A library to train, evaluate, interpret, and productionize decision forest models such as Random Forest and Gradient Boosted Decision Trees.
lucidrains/bottleneck-transformer-pytorch15,133
Language:
Python
Stars:
677
Forks:
81
Description:
Implementation of Bottleneck Transformer in Pytorch.
understandable-machine-intelligence-lab/Quantus15,136
Language:
Jupyter Notebook
Stars:
677
Forks:
94
Description:
[JMLR 2023] Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations.
yjn870/SRCNN-pytorch15,143
Language:
Python
Stars:
676
Forks:
134
Description:
PyTorch implementation of Image Super-Resolution Using Deep Convolutional Networks (ECCV 2014).
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModel Development
SubcategoryArchitecture
KeywordsImage production
Stars677
Forks109
Contributors1
Created date2017-12-01
Updated date2026-09-16
Stars in 1 day0
Stars in 7 days0
Rank15,128
Previous rank14,953
Rank change-175
7-day stars rank14,822
Previous 7-day stars rank14,840
7-day stars rank change18
Total stars rank15,267
Previous total stars rank15,240
Total stars rank change-27
README summary

SN-GAN (spectral normalization GAN) in PyTorch Based on the paper "Spectral Normalization for Generative Adversarial Networks" by Takeru Miyato, Toshiki Kataoka, Masanori Koyama, Yuichi Yoshida ICLR 2018 preprint: CIFAR-10 Samples Implementation Details This code implements both DCGAN-like and ResNet GAN architectures. In addition, training with standard, Wasserstein, and hinge losses is possible. To get ResNet working, initialization (Xavier/Glorot) turned out to be very important. Training Train ResNet generator and discriminator with hinge loss: Train ResNet generator

and discriminator with wasserstein loss: Train DCGAN generator and discriminator with cross-entropy loss:

Frequently asked questions

How many stars and forks are recorded?

christiancosgrove/pytorch-spectral-normalization-gan has 677 stars and 109 forks.

What is the repository rank?

christiancosgrove/pytorch-spectral-normalization-gan is ranked 15,128.

What language and category are recorded?

christiancosgrove/pytorch-spectral-normalization-gan has 677 stars, uses Python and belongs to Model Development.

Which repository is closest in rank?

christiancosgrove/pytorch-spectral-normalization-gan is compared with google/yggdrasil-decision-forests, ranked 15,129 with 677 stars.

README

SN-GAN (spectral normalization GAN) in PyTorch

Based on the paper "Spectral Normalization for Generative Adversarial Networks" by Takeru Miyato, Toshiki Kataoka, Masanori Koyama, Yuichi Yoshida

ICLR 2018 preprint: https://openreview.net/forum?id=B1QRgziT-

CIFAR-10 Samples

Implementation Details

This code implements both DCGAN-like and ResNet GAN architectures. In addition, training with standard, Wasserstein, and hinge losses is possible.

To get ResNet working, initialization (Xavier/Glorot) turned out to be very important.

Training

Train ResNet generator and discriminator with hinge loss: python main.py --model resnet --loss hinge

Train ResNet generator and discriminator with wasserstein loss: python main.py --model resnet --loss wasserstein

Train DCGAN generator and discriminator with cross-entropy loss: python main.py --model dcgan --loss bce

Nearby in the ranking
Similar items