[LEADERG APP] CycleGAN

Area (Language):

大陆港澳 (简体中文)

台灣 (繁體中文)

 

 [Introduction]

 

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.  

 

APP.png

 

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.

 

Note:

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.

 

visdom.png

 

Training :

 

 

train.png  

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.

 

Inference:

 

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.

 

inference.png


Recommended Article

1.
LEADERG APP - AI Software (No Code, APP User Interface)

2.
LEADERG AI ZOO - Advanced AI Software (Low Code, Jupyter Lab User Interface)

3.
LEADERG AI Computer ( Deep Learning, PC, workstation, server, NVIDIA GPU, TESLA A100, RTX-3090-24G, Intel VPU, GPU Server

4.
AI Training Courses

Trial of LEADERG APP

Welcome to contact us for 15 days trial of LEADERG APP.
Email: leaderg@leaderg.com

How to Buy

Welcome to contact us for quotation. We will help you buy right products.
Email: leaderg@leaderg.com