fxia22 / Pixeldtgan
Licence: mit
A torch implementation of "Pixel-Level Domain Transfer"
Stars: ✭ 248
Programming Languages
lua
6591 projects
Projects that are alternatives of or similar to Pixeldtgan
Cat Generator
Generate cat images with neural networks
Stars: ✭ 354 (+42.74%)
Mutual labels: gan, torch
Face Generator
Generate human faces with neural networks
Stars: ✭ 266 (+7.26%)
Mutual labels: gan, torch
Deepnudecli
DeepNude Command Line Version With Watermark Removed
Stars: ✭ 112 (-54.84%)
Mutual labels: gan, torch
Colorizer
Add colors to black and white images with neural networks (GANs).
Stars: ✭ 69 (-72.18%)
Mutual labels: gan, torch
Torchelie
Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch.
Stars: ✭ 98 (-60.48%)
Mutual labels: gan, torch
Cyclegan
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Stars: ✭ 10,933 (+4308.47%)
Mutual labels: gan, torch
Gan steerability
On the "steerability" of generative adversarial networks
Stars: ✭ 225 (-9.27%)
Mutual labels: gan
Gif
GIF is a photorealistic generative face model with explicit 3D geometric and photometric control.
Stars: ✭ 233 (-6.05%)
Mutual labels: gan
Anogan Tf
Unofficial Tensorflow Implementation of AnoGAN (Anomaly GAN)
Stars: ✭ 218 (-12.1%)
Mutual labels: gan
Warpgan
(CVPR 2019 Oral) Style Transfer with Geometric Deformation
Stars: ✭ 215 (-13.31%)
Mutual labels: gan
Srgan
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Stars: ✭ 2,641 (+964.92%)
Mutual labels: gan
Nlpgnn
1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and GraphSAGE based on message passing.
Stars: ✭ 221 (-10.89%)
Mutual labels: gan
The Gan World
Everything about Generative Adversarial Networks
Stars: ✭ 243 (-2.02%)
Mutual labels: gan
Floorplantransformation
Raster-to-Vector: Revisiting Floorplan Transformation
Stars: ✭ 243 (-2.02%)
Mutual labels: torch
Adgan
The Implementation of paper "Controllable Person Image Synthesis with Attribute-Decomposed GAN"
Stars: ✭ 239 (-3.63%)
Mutual labels: gan
Echotorch
A Python toolkit for Reservoir Computing and Echo State Network experimentation based on pyTorch. EchoTorch is the only Python module available to easily create Deep Reservoir Computing models.
Stars: ✭ 231 (-6.85%)
Mutual labels: torch
Pixel Level Domain Transfer
A torch implementation of "Pixel-Level Domain Transfer". based on dcgan.torch.
Dataset
The dataset used is "LookBook", from Donggeun Yoo.
Training
To train the model, put the LOOKBOOK dataset under repository, resize images to 64*64. Prepare the dataset using prepare_data.ipynb
.
Then run
th main.lua
You can tune the parameters, such as number of filters, optimizer, etc.
Example results
Example results on LOOKBOOK dataset(top), left is input, right is generated clothes. Results on a similar dataset (bottom). More results will be added soon.
Monitor the performance
- Install display package with:
luarocks install https://raw.githubusercontent.com/szym/display/master/display-scm-0.rockspec
- Start the server with:
th -ldisplay.start
- Open this URL in your browser:
http://localhost:8000
Below shows the results after 7 epochs, each 3*1 block is generated cloth, true cloth, input image. Errors of G, D, and A network will be plotted.
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].