Minor changes of base repository.

A short writeup and example images are up on my blog.

In an attempt to learn Tensorflow I've implemented an Image Transformation Network as described in Perceptual Losses for Real-Time Style Transfer and Super-Resolution by Johnson et al.

This technique uses loss functions based on a perceptual similarity and style similarity as described by Gatys et al to train a transformation network to synthesize the style of one image with the content of arbitrary images. After it's trained for a particular style it can be used to generate stylized images in one forward pass through the transformer network as opposed to 500-2000 forward + backward passes through a pretrained image classification net which is the direct approach.

First get the dependecies (COCO training set images and VGG model weights):

./get_files.sh

To generate an image directly from style and content, typically to explore styles and parameters:

python neural_style.py --CONTENT_IMAGE content.png --STYLE_IMAGES style.png

Also see other settings and hyperparameters in neural_style.py

To train a model for fast stylizing:

python fast_neural_style.py --TRAIN_IMAGES_PATH coco_img_path --STYLE_IMAGES style.png --BATCH_SIZE 4

Where --TRAIN_IMAGES_PATH points to a directory of JPEGs to train the model. The paper uses the COCO image dataset (13GB). With my 2GB GTX960 card I can do a batch_size of 3 images. The paper trains the model for 2 epochs (160.000/BATCH_SIZE iteration).

To generate images fast with an already trained model:

python fast_neural_style.py --CONTENT_IMAGES path_to_images_to_transform

• Python3.x
• Tensorflow
• VGG-19 model
• COCO dataset

• [Chainer implementation] (https://github.com/yusuketomoto/chainer-fast-neuralstyle)
• [Tensorflow Neural style implementation] (https://github.com/anishathalye/neural-style)