Metadata-Version: 2.1
Name: improvedgan-pytorch
Version: 0.1.0
Summary: 
Author: Lucas Gomes
Author-email: lggomes007@gmail.com
Requires-Python: >=3.10,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: imageio (>=2.31.1,<3.0.0)
Requires-Dist: matplotlib (>=3.7.1,<4.0.0)
Requires-Dist: numpy (>=1.25.0,<2.0.0)
Requires-Dist: pillow (>=9.5.0,<10.0.0)
Requires-Dist: six (>=1.16.0,<2.0.0)
Requires-Dist: tensorboardx (>=2.6.1,<3.0.0)
Requires-Dist: torch (>=2.0.1,<3.0.0)
Requires-Dist: torchvision (>=0.15.2,<0.16.0)
Description-Content-Type: text/markdown

# ImproveGan-pytorch
Improved Techniques for Training GANs for cifar10 dataset  
This is an implementation of Semi-supervised generative adversarial network in the paper Improved Techniques for Training GANs for cifar10 dataset.  
# Related  
Origin paper:https://arxiv.org/abs/1606.03498  
Official Implementation(Theano):https://github.com/openai/improved-gan  
# Requirement  
python3.5  
pytorch 1.1.0  
cuda8.0  
torchvision  
# Run
python3 train.py  
Default Set:config.py
# Result  
Test best acc:**79.64%** .Achieve the accuracy of the original paper.
# loss curve  
![](./results/test.png)
![](./results/train.png)
![](./results/loss.png)
![](./results/unloss.png)
![](./results/gen_loss.png)
# Train process of Gen img  
![image](./results/result.gif)



