Chainer implementation of "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" Fast artistic style transfer by using feed forward network.
checkout resize-conv branch which provides better result.
nput image size: 1024x768
process time(CPU): 17.78sec (Core i7-5930K)
process time(GPU): 0.994sec (GPU TitanX)
Requirement$ pip install chainer PrerequisiteDownload 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 TrainNeed 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> Generatepython 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.
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_colors
A collection of pre-trained models Fashizzle Dizzle created pre-trained models collection repository, chainer-fast-neuralstyle-models . You can find a variety of models.
Difference from paper No Backward Compatibility Jul. 19, 2016This version is not compatible with the previous versions. You can't use models trained by the previous implementation. Sorry for the inconvenience!
LicenseMIT
ReferenceCodes written in this repository based on following nice works, thanks to the author.