1
#
singan
Here are 11 public repositories matching this topic...
Reimplementing the paper "SinGAN: Learning a Generative Model from a Single Natural Image"
-
Updated
May 14, 2020 - Python
pytorch implementation
-
Updated
Jun 23, 2020 - Jupyter Notebook
New Transformer network-based GAN for video generation.
-
Updated
Jun 1, 2020 - Jupyter Notebook
Flux.jl implementation of (part of) "SinGAN: Learning a Generative Model from a Single Natural Image"
-
Updated
Jan 11, 2020 - Julia
"SinGAN : Learning a Generative Model from a Single Natural Image" in TensorFlow 2
deep-learning
neural-network
tensorflow
keras
gan
editing
image-generation
harmonization
tensorflow2
singan
-
Updated
May 18, 2020 - Python
Inofficial implementation of the paper "SinGAN: Learning a Generative Model from a Single Natural Image"
university-project
pytorch
image-editing
generative-adversarial-network
gan
image-translation
re-implementation
image-super-resolution
singan
single-image-animation
image-harmonization
inoffical
-
Updated
Jun 24, 2020 - Python
Learning a generative model from a single natural image
-
Updated
Dec 10, 2019 - Python
Improve this page
Add a description, image, and links to the singan topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the singan topic, visit your repo's landing page and select "manage topics."
In config.py:
parser.add_argument('--padd_size',type=int,help='net pad size',default=0)#math.floor(opt.ker_size/2)I'm wondering why you commented out the code for same padding to use valid padding instead? Is this important? (I checked both paper and ICCV talk, and it wasn't mentioned)