duxingren14 / Dualgan
Licence: apache-2.0
DualGAN-tensorflow: tensorflow implementation of DualGAN
Stars: ✭ 230
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Dualgan
Gulp Image
Optimize PNG, JPEG, GIF, SVG images with gulp task.
Stars: ✭ 213 (-7.39%)
Mutual labels: image
Pica
Resize image in browser with high quality and high speed
Stars: ✭ 2,900 (+1160.87%)
Mutual labels: image
React Native Auto Height Image
🖼️React native auto height image
Stars: ✭ 219 (-4.78%)
Mutual labels: image
Lazyload Image
HTMLImageElement extension for lazy loading.
Stars: ✭ 208 (-9.57%)
Mutual labels: image
Slideimageview
Simple and convenient library that allows you to slide images through a view.
Stars: ✭ 227 (-1.3%)
Mutual labels: image
React Native Perspective Image Cropper
Perform custom crop, resizing and perspective correction 📐🖼
Stars: ✭ 223 (-3.04%)
Mutual labels: image
Rskimagecropper
An image cropper / photo cropper for iOS like in the Contacts app with support for landscape orientation.
Stars: ✭ 2,371 (+930.87%)
Mutual labels: image
Transfer Learning Suite
Transfer Learning Suite in Keras. Perform transfer learning using any built-in Keras image classification model easily!
Stars: ✭ 212 (-7.83%)
Mutual labels: image
Use Image Color
🎨 A hook to grab a color palette from images. Render a skeleton color while your original image still loading.
Stars: ✭ 222 (-3.48%)
Mutual labels: image
Dhash
Python library to calculate the difference hash (perceptual hash) for a given image, useful for detecting duplicates
Stars: ✭ 209 (-9.13%)
Mutual labels: image
React Worker Image
React component to fetch image resources via web workers 🤖🤖
Stars: ✭ 226 (-1.74%)
Mutual labels: image
Bv
Quickly view satellite imagery, hyperspectral imagery, and machine learning image outputs directly in your iTerm2 terminal.
Stars: ✭ 215 (-6.52%)
Mutual labels: image
Craft Imageoptimize
Automatically create & optimize responsive image transforms, using either native Craft transforms or a service like Imgix, with zero template changes.
Stars: ✭ 227 (-1.3%)
Mutual labels: image
Vue Img Cutter
简单易用的vue图片裁剪插件,支持移动图像,裁剪图片,放大缩小图片,上下左右移动,固定比例,固定尺寸,远程图片裁剪,只需要很少的代码就可以实现裁剪功能,也可以通过调整参数以适应你自己的业务需求。
Stars: ✭ 220 (-4.35%)
Mutual labels: image
ICCV paper of DualGAN
DualGAN: unsupervised dual learning for image-to-image translation
please cite the paper, if the codes has been used for your research.
architecture of DualGAN
How to setup
Prerequisites
-
Linux
-
Python (2.7 or later)
-
numpy
-
scipy
-
NVIDIA GPU + CUDA 8.0 + CuDNN v5.1
-
TensorFlow 1.0 or later
Getting Started
steps
- clone this repo:
git clone https://github.com/duxingren14/DualGAN.git
cd DualGAN
- download datasets (e.g., sketch-photo), run:
bash ./datasets/download_dataset.sh sketch-photo
- download pre-trained model (e.g., sketch-photo), run:
bash ./checkpoint/download_ckpt.sh sketch-photo
- train the model:
python main.py --phase train --dataset_name sketch-photo --image_size 256 --lambda_A 1000.0 --lambda_B 1000.0 --epoch 100
- test the model:
python main.py --phase test --dataset_name sketch-photo --image_size 256 --lambda_A 1000.0 --lambda_B 1000.0 --epoch 100
optional
Similarly, run experiments on facades dataset with the following commands:
bash ./datasets/download_dataset.sh facades
python main.py --phase train --dataset_name facades --lambda_A 1000.0 --lambda_B 1000.0 --epoch 100
python main.py --phase test --dataset_name facades --lambda_A 1000.0 --lambda_B 1000.0 --epoch 100
For thoese who cannot download datasets or pretrained models using the scripts, please try manual downloading from the link as below:
all datasets from google drive
pretrained models from google drive
Experimental results:
Acknowledgments
Codes are built on the top of pix2pix-tensorflow and DCGAN-tensorflow. Thanks for their precedent contributions!
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].