You can train your model with your own style images. This can be done in three steps.
Get ready with your own style images in a directory and download the trained VGG model checkpoint from here: http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz:
//Setting up your own images$ image_stylization_create_dataset \ --vgg_checkpoint=/path/to/vgg_16.ckpt \ --style_files=/path/to/style/images/*.jpg \ --output_file=/tmp/image_stylization/style_images.tfrecord
Then, you can start training the model:
//Training a model$ image_stylization_train \ --train_dir=/tmp/image_stylization/run1/train --style_dataset_file=/tmp/image_stylization/style_images.tfrecord \ --num_styles=<NUMBER_OF_STYLES> \ --vgg_checkpoint=/path/to/vgg_16.ckpt ...
