[PYTHON] Train UGATIT with your own dataset

UGATIT is a state-of-the-art machine learning image converter. * Paper * GitHub project page teaser.png You can train this model on your own dataset.

For this training, we recommend a Google Colaboratory notebook with a free GPU. This is because UGATIT requires powerful computing power.

1, clone from the GitHub project page above.

git clone https://github.com/taki0112/UGATIT.git
cd UGATIT
  1. Install TensorFlow 1.14 (without TensorFlow1 because this model was created with TensorFlow1 instead of TensorFlow2.0).
pip install tensorflow-gpu==1.14
  1. Create your own dataset. We recommend using 6200 images (TrainA (DomainA): 3000, TrainB (DomainB): 3000, TestA (DomainA): 100, TestB (DomainB): 100). This is because the selfie2anime dataset in the original project has this amount of images. The size of the image is not important. UGATITutils will automatically resize the image. Create a dataset directory and create a directory for each domain in it.
スクリーンショット 2020-06-24 7.47.14.png Specify the directory name of the dataset (for example, “selfly2anime”). Then place the dataset directory in the UGATIT directory.

4, run the train script. You must specify your own dataset name in the “— dataset” argument.

python main.py --dataset your_dataset_name --phase train

Training starts, and the result image and checkpoint are output.

Any question?

Recommended Posts

Train UGATIT with your own dataset
Train Stanford NER Tagger with your own data
Solve your own maze with Q-learning
Solve your own maze with DQN
Your own Twitter client made with Django
[Reinforcement learning] DQN with your own library
Create your own DNS server with Twisted
Create your own Composite Value with SQLAlchemy
To import your own module with jupyter
Try to make your own AWS-SDK with bash
Extend and inflate your own Deep Learning dataset
Make your own module quickly with setuptools (python)
Annotate your own data to train Mask R-CNN
Make your own music player with Bottle0.13 + jPlayer2.5!
Steps to install your own library with pip
Create your own exception
Memo to create your own Box with Pepper's Python
Call your own C library with Go using cgo
Define your own distance function with k-means of scikit-learn
Until you annotate your own dataset and detect an object with EfficientDet ~ Character face detection ~
Until you can install your own Python library with pip
Try sorting your own objects with priority queue in Python
Run the intellisense of your own python library with VScode.
Learn "x86 architecture learned with your own emulator" with Manjaro (Linux)
Reinforcement learning 23 Create and use your own module with Colaboratory
Try HeloWorld in your own language (with How to & code)
Operate your website with Python_Webbrowser
Create your own Django middleware
Make your own VPC with a Single Public Subnet Only with boto
[Introduction to StyleGAN] Unique learning of anime with your own machine ♬
How to make your own domain site with heroku (free plan)
Introduction to Deep Learning (2) --Try your own nonlinear regression with Chainer-
Draw your own Drop Indicator with PySide (Realize QProxyStyle with black magic)