Generalized Loss-Sensitive Generative Adversarial Networks (GLS-GAN) in PyTorch with gradient penalty, including both LS-GAN and WGAN as special cases.
-
Updated
Mar 4, 2018 - Python
#
ls-gan
Here are 3 public repositories matching this topic...
PyTorch implementations of Generative Adversarial Network series
gan
infogan
dcgan
ebgan
wgan
pytorch-tutorial
began
wgan-gp
ls-gan
pytorch-implementation
cyclegan-pytorch
-
Updated
Sep 3, 2021 - Jupyter Notebook
Implemented Vanilla RNN and LSTM networks, combined these with pretrained VGG-16 on ImageNet to build image captioning models on Microsoft COCO dataset. Explored use of image gradients for generating new images and techniques used are Saliency Maps, Fooling Images and Class Visualization. Implemented image Style Transfer technique from 'Image St…
numpy
pytorch
lstm
gan
style-transfer
rnn
mnist-dataset
saliency-map
dc-gan
cs231n-assignment
fooling-images
class-visualization
coco-dataset
ls-gan
microsoft-coco
-
Updated
Aug 31, 2018 - Jupyter Notebook
Improve this page
Add a description, image, and links to the ls-gan topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the ls-gan topic, visit your repo's landing page and select "manage topics."