CycleGAN is a well-known algorithm published in ICCV2017 image-to-image translation. The biggest feature is that it does not require training data to be paired. It only needs to provide images of different domains to successfully train image conversion between different domains.

It can be applied to various applications such as transforming streets with semantic tags into realistic images, transforming satellite images into map images, transforming scenes from day to night, turning black and white images into color images, and synthesizing real product images with contour maps.



[Operation steps and instructions]


APP is mainly divided into four major functions, data preparation, training, inference, and others.  




Data preparation :


Select Dataset : Select the data set for AI learning.

If you want to train your own images, please click View to see the data folder, please copy a default horse-zebra folder and change it to your own data name. At this time, please do not delete any sub-folders and files in the folder.


If you want to learn the conversion between horse and zebra

trainA: The training image of the horse.

trainB: The training image of the zebra.

testA: Test image of horse.

testB: Test image of zebra.



1. It is recommended that the image length and width be the same, square, if not the same, you can zoom or crop.

2. The image file and its attached file name must be .jpg.  


Select dataset.png


Preparation before training :


Before training, please click 1. visdom server and 2. visdom server browser in order, as shown in the figure below, please don't click x to close it. Please keep it open during training.

After starting the training, the training loss curve and other information will be post to the visdom server and displayed on the visdom server browser.




Training :




Click 3. train to start training. During the training process, you can use the 2. visdom server browser opened in the previous step to watch the loss curve and the training effect.


During training, the parameters that can be set are as follows:

    Continue training : If you want to continue training, please tick it, and the training will automatically load the last model and continue training (latest_net_G_A.pth、latest_net_G_B.pth、latest_net_D_A.pth、latest_net_D_B.pth). Otherwise, don't tick it.


    Dataroot : The training image path. Press view to see trainA and trainB. The training images are in the folder.


    Checkpoints dir : The folder of the training model, click view to see the folder.


    GPU ID : If your device supports NVIDIA GPU accelerated computing, please set the GPU ID, if you use the 0th GPU, set it to 0, and use the 0th and 1st GPU to set it to 0, 1. If NVIDIA GPU accelerated computing is not supported, set to -1.


    Batch size : The number of training examples in one forward/backward pass.


    N epochs : Set the number of epochs for training. The total number of epochs for training will add an additional 100 epochs, using a learning rate that decays linearly to 0.


    Save epoch freq : The number of frequency epochs to store the model.




Infer the entire folder.

Click 4. inference folder, select the model, and start the inference. After the inference is completed, pop out of the browser to view the inference results.


The inference parameters are as follows :

    A->B: Convert A to B; B->A: Convert B to A. For example, during training, A is a zebra and B is a horse. When the inference is selected A->B, the zebra is turned into a horse.


    Inference folder : Shows the folder path of the inferred image. This folder is the testA and testB folders in the data preparation step.


    GPU ID : If your device supports NVIDIA GPU accelerated computing, please set the GPU ID, if you use the 0th GPU, set it to 0, and use the 0th and 1st GPU to set it to 0, 1. If NVIDIA GPU accelerated computing is not supported, set to -1.


App4AI CycleGAN inference.png



Contact Us and How to Buy

Welcome to contact us. Please refer to the following link:


Recommended Article

App4AI - AI Software - Windows Edition

App4AI - AI Software - Linux Edition



Thanks for our customers

Taiwan University, Tsing Hua University, Yang Ming Chiao Tung University, Cheng Kung University, Taipei Medical University, Taipei University of Nursing and Health Sciences, National Chung Hsing University, Chi Nan University, Ilan University, United University, Defence University, Military Academy, Naval Academy, Feng Chia University, Chang Gung University, I-Shou University, Shih Chien University, Taiwan University of Science and Technology, Taichung University of Science and Technology, Yunlin University of Science and Technology, Chin-Yi University of Science, Formosa University, Pintung University of Science and Technology, Kaohsiung University of Science and Technology, Chaoyang University of Technology, Ming Chi University of Technology, Southern Taiwan University of Science and Technology, China University of Technology, Gushan Senior High School, Taipei Veterans General Hospital, Chang Gung Medical Foundation, Tzu Chi Medical Foundation, E-Da Hospital, Industry Technology Research Institute, Institute for Information Industry, Chung-Shan Institute of Science and Technology, Armaments Bureau, Ministry of Justice Investigation Bureau, Institute of Nuclear Energy Research, Endemic Species Research Institute, Institute of Labor, Occupational Safety And Health, Metal Industries Research & Development Centre, Taiwan Instrument Research Institute, Automotive Research & Testing Center, Taiwan Water Corporation, Taiwan Semiconductor Manufacturing Co., Ltd., United Microelectronics Corp., Nanya Technology, Winbond Electronics Corp., Xintec Inc., Arima Lasers Corporation, AU Optronics Corporation, Innolux Corporation, HannStar Display Corporation, Formosa Plastics Group., Formosa Technologies Corporation, Nan Ya Plastics Corp., Formosa Chemicals & Fibre Corporation, Chinese Petroleum Corporation, Logitech, ELAN Microelectronics Corp., Lextar Electronics Corporation, Darfon Electronics Corp., WPG Holdings, Mirle Automation Corporation, Symtek Automation Asia Co., Ltd, ChipMOS Technologies Inc., Dynapack International Technology Corporation, Primax Electronics Ltd., Feng Hsin Steel, China Ecotek, Grade Upon Technology Corp., AAEON Technology Inc., Stark Technology, Inc., Horng Terng Automation Co., Ltd., Zhen Ding Technology Holding Ltd, Boardtek Electronics Corporation, MiTAC International Corporation, Allion Labs, Inc., Sound Land Corp., Hong Hu Tech, etc.