AI Rank
EN
← 开源
xiaowei-hu

CycleGAN-tensorflow

Tensorflow implementation for learning an image-to-image translation without input-output pairs. https://arxiv.org/pdf/1703.10593.pdf

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
712
Star
291
Fork
+0
本周
2
贡献者
创建于 2017-04-17 · 更新于 2026-08-01 · 今日第 14682 名
主要开发者
cyberj0gmathandy

xiaowei-hu/CycleGAN-tensorflow 排名第 14,682，有 712 个星标。

同类别比较

xiaowei-hu/CycleGAN-tensorflow 排名第 14,682，此处有 8 个同类条目；lezcano/geotorch 排名第 14,681。

同类别比较
名称排名指标
dmlc/minerva14,677
语言:
C++
星标数:
712
分叉数:
173
简介:
Minerva: a fast and flexible tool for deep learning on multi-GPU. It provides ndarray programming interface, just like Numpy. Python bindings and C++ bindings are both available. The resulting code can be run on CPU or GPU. Multi-GPU support is very easy.
hackthemarket/gym-trading14,679
语言:
Jupyter Notebook
星标数:
712
分叉数:
208
简介:
Environment for reinforcement-learning algorithmic trading models
jiny2001/dcscn-super-resolution14,680
语言:
Python
星标数:
712
分叉数:
218
简介:
A tensorflow implementation of "Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network", a deep learning based Single-Image Super-Resolution (SISR) model.
lezcano/geotorch14,681
语言:
Python
星标数:
712
分叉数:
36
简介:
Constrained optimization toolkit for PyTorch
ajtulloch/dnngraph14,686
语言:
Haskell
星标数:
711
分叉数:
59
简介:
A DSL for deep neural networks, supporting Caffe and Torch
codefuse-ai/MFTCoder14,687
语言:
Python
星标数:
711
分叉数:
69
简介:
High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs. This work has been accepted by KDD 2024.
google/edward214,691
语言:
Jupyter Notebook
星标数:
711
分叉数:
77
简介:
A simple probabilistic programming language.
OptMLGroup/VRP-RL14,699
语言:
Python
星标数:
710
分叉数:
234
简介:
Reinforcement Learning for Solving the Vehicle Routing Problem
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
关键词Image production
星标数712
分叉数291
贡献者2
创建日期2017-04-17
更新日期2026-08-01
1 天星标数0
7 天星标数0
排名14,682
上次排名14,528
排名变化-154
7 天星标排名14,601
上次 7 天星标排名14,611
7 天星标排名变化10
总星标排名14,701
上次总星标排名14,673
总星标排名变化-28
国家China
README 摘录

The method is proposed by Jun-Yan Zhu in Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkssee. 0 Getting Started Installation Install tensorflow from Clone this repo: Train Download a dataset (e. zebra and horse images from ImageNet): Train a model: Use tensorboard to visualize the training details: Test Finally, test the model: Training and Test Details To train a model, Models are saved to (can be changed by passing ). To test the model, Datasets Download the datasets

using the following script: : 400 images from the CMP Facades dataset. : 2975 images from the Cityscapes training set. : 1096 training images scraped from Google Maps. : 939 horse images and 1177 zebra images downloaded from ImageNet using keywords and . : 996 apple images and 1020 orange images downloaded from ImageNet using keywords and . : 1273 summer Yosemite images and 854 winter Yosemite images were downloaded using Flickr API. , , , : The art images were downloaded from Wikiart. The real photos are downloaded from Flickr using

combination of tags *landscape* and *landscapephotography*. The training set size of each class is Monet:1074, Cezanne:584, Van Gogh:401, Ukiyo-e:1433, Photographs:6853. : both classe of images were downlaoded from Flickr. The training set size of each class is iPhone:1813, DSLR:3316. Reference The torch implementation of CycleGAN, The tensorflow implementation of pix2pix,

常见问题

记录了多少星标和分叉？

xiaowei-hu/CycleGAN-tensorflow 有 712 个星标和 291 个分叉。

仓库排名是多少？

xiaowei-hu/CycleGAN-tensorflow 排名第 14,682。

记录的语言和类别是什么？

xiaowei-hu/CycleGAN-tensorflow 有 712 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

xiaowei-hu/CycleGAN-tensorflow 与 lezcano/geotorch 比较，后者排名第 14,681，有 712 个星标。

README

CycleGAN

Tensorflow implementation for learning an image-to-image translation without input-output pairs. The method is proposed by Jun-Yan Zhu in Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkssee. For example in paper:

Update Results

The results of this implementation:

  • Horses -> Zebras

  • Zebras -> Horses

You can download the pretrained model from this url and extract the rar file to ./checkpoint/.

Prerequisites

  • tensorflow r1.1
  • numpy 1.11.0
  • scipy 0.17.0
  • pillow 3.3.0

Getting Started

Installation

git clone https://github.com/xhujoy/CycleGAN-tensorflow
cd CycleGAN-tensorflow

Train

  • Download a dataset (e.g. zebra and horse images from ImageNet):
bash ./download_dataset.sh horse2zebra
  • Train a model:
CUDA_VISIBLE_DEVICES=0 python main.py --dataset_dir=horse2zebra
  • Use tensorboard to visualize the training details:
tensorboard --logdir=./logs

Test

  • Finally, test the model:
CUDA_VISIBLE_DEVICES=0 python main.py --dataset_dir=horse2zebra --phase=test --which_direction=AtoB

Training and Test Details

To train a model,

CUDA_VISIBLE_DEVICES=0 python main.py --dataset_dir=/path/to/data/

Models are saved to ./checkpoints/ (can be changed by passing --checkpoint_dir=your_dir).

To test the model,

CUDA_VISIBLE_DEVICES=0 python main.py --dataset_dir=/path/to/data/ --phase=test --which_direction=AtoB/BtoA

Datasets

Download the datasets using the following script:

bash ./download_dataset.sh dataset_name
  • facades: 400 images from the CMP Facades dataset.
  • cityscapes: 2975 images from the Cityscapes training set.
  • maps: 1096 training images scraped from Google Maps.
  • horse2zebra: 939 horse images and 1177 zebra images downloaded from ImageNet using keywords wild horse and zebra.
  • apple2orange: 996 apple images and 1020 orange images downloaded from ImageNet using keywords apple and navel orange.
  • summer2winter_yosemite: 1273 summer Yosemite images and 854 winter Yosemite images were downloaded using Flickr API. See more details in our paper.
  • monet2photo, vangogh2photo, ukiyoe2photo, cezanne2photo: The art images were downloaded from Wikiart. The real photos are downloaded from Flickr using combination of tags landscape and landscapephotography. The training set size of each class is Monet:1074, Cezanne:584, Van Gogh:401, Ukiyo-e:1433, Photographs:6853.
  • iphone2dslr_flower: both classe of images were downlaoded from Flickr. The training set size of each class is iPhone:1813, DSLR:3316. See more details in our paper.

Reference

排名相邻
同类项目