styloint / chainer-fast-neuralstyle

Chainer implementation of "Perceptual Losses for Real-Time Style Transfer and Super-Resolution".

Chainer implementation of "Perceptual Losses for Real-Time Style Transfer and Super-Resolution"

Fast artistic style transfer by using feed forward network.

What changes from yusekemoto version

• Insteand of using tanh as activation function, I use sigmoid. Using tanh, I was having a lot of artefacts (black hole, white hole, points, etc ...) Using sigmoid seems to have solve the issue. So all the models trained with yusekemoto version should not work.
• Loss graph and results saved at each checkpoint.
• Can resume a training
• If the output path for saving the models contains directory that does not exists, they are created
• Compatible with chainer 4.1
• Train with size 512 by default and save checkpoints every 1000 iteration

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

Requirement

• Chainer

$ pip install chainer

Prerequisite

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

Train

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>

Generate

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

• 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

Transfer only style but not color (--keep_colors option)

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

A collection of pre-trained models

Coming soon !

Difference from paper

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

License

MIT

Reference

• 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.