https://github.com/gs18113/AdaIN-TensorFlow2

AdaIN(https://arxiv.org/abs/1703.06868) implementation with TensorFlow 2
https://github.com/gs18113/AdaIN-TensorFlow2

Last synced: about 2 months ago
JSON representation

AdaIN(https://arxiv.org/abs/1703.06868) implementation with TensorFlow 2

• Host: GitHub
• URL: https://github.com/gs18113/AdaIN-TensorFlow2
• Owner: gs18113
• Created: 2019-10-27T08:58:03.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2019-11-01T08:27:11.000Z (about 5 years ago)
• Last Synced: 2024-08-01T03:17:15.598Z (4 months ago)
• Language: Python
• Size: 39.1 KB
• Stars: 6
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-tensorflow-2 - Arbitrary Style Transfer in Real-time

README

        
# AdaIN-TensorFlow2

AdaIN(from the paper Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization, https://arxiv.org/abs/1703.06868) implementation with TensorFlow 2

Original PyTorch code: https://github.com/naoto0804/pytorch-AdaIN

Includes TFLite conversion for mobile/embedded usage.

## Requirements

* tensorflow >= 2.0.0

* tensorflow_datasets

## Note

* **Most of the code is from naoto0804/pytorch-AdaIN https://github.com/naoto0804/pytorch-AdaIN**.

* This code was written for studying, so the code may be hard to understand. I'll try my best to improve code readability.

## Usage

### Download style images

```

cd STYLE/IMAGE/DIRECTORY/

wget http://web.fsktm.um.edu.my/~cschan/source/ICIP2017/wikiart.zip

unzip wikiart.zip

```

### Train

```

python3 train.py -exp_name EXP_NAME [-lr LEARNING_RATE] [-batch_size BATCH_SIZE] [-output_dir OUTPUT_DIR] [-save_every SAVE_EVERY] [-save_tflite SAVE_TFLITE]

```

Check out the code for more training options.

## TODO

* Generate TFLite model from checkpoints

* Color preserving

* Style interpolation

* Different style for different region