Fast artistic style transfer by using feed forward network.

checkout resize-conv branch which provides better result.

• input image size: 1024x768
• process time(CPU): 17.78sec (Core i7-5930K)
• process time(GPU): 0.994sec (GPU TitanX)

• Chainer

$ pip install chainer

Download VGG16 model and convert it into smaller file so that we use only the convolutional layers which are 10% of the entire model.

sh setup_model.sh

Need to train one image transformation network model per one style target. According to the paper, the models are trained on the Microsoft COCO dataset.

python train.py -s <style_image_path> -d <training_dataset_path> -g <use_gpu ? gpu_id : -1>

python generate.py <input_image_path> -m <model_path> -o <output_image_path> -g <use_gpu ? gpu_id : -1>

This repo has pretrained models as an example.

• example:

python generate.py sample_images/tubingen.jpg -m models/composition.model -o sample_images/output.jpg

or

python generate.py sample_images/tubingen.jpg -m models/seurat.model -o sample_images/output.jpg

python generate.py <input_image_path> -m <model_path> -o <output_image_path> -g <use_gpu ? gpu_id : -1> --keep_colors

Fashizzle Dizzle created pre-trained models collection repository, chainer-fast-neuralstyle-models. You can find a variety of models.

• Convolution kernel size 4 instead of 3.
• Training with batchsize(n>=2) causes unstable result.

This version is not compatible with the previous versions. You can't use models trained by the previous implementation. Sorry for the inconvenience!

MIT

• Perceptual Losses for Real-Time Style Transfer and Super-Resolution

Codes written in this repository based on following nice works, thanks to the author.

• chainer-gogh Chainer implementation of neural-style. I heavily referenced it.
• chainer-cifar10 Residual block implementation is referred.