Tensorflow implementation of the fast feed-forward neural style transfer network by Johnson et al.

Here is an example of styling a photo of San Francisco with Van Gogh's Starry Night

The code is based off this paper by Johnson et al which in turn builds off of A Neural Algorithm of Artistic Style by Gatys et al.

This implementation uses Instance Norm described by Ulyanov et al and Resize-Convolution from Odena et al.

Takes a few hours to train on a P2 instance on AWS and image generation takes a few seconds on a Macbook Pro. Training image dataset was from MS COCO validation set and uses the VGG19 network for texture and style loss

1. Tensorflow 0.10
2. pip install:

• scikit-image
• numpy 1.11

1. Go to the project root (there is a pretrained model in the /data directory)
2. Run:

$ python style.py --input=path_to_image.jpg --output=your_output_file.jpg

1. Download VGG19 weights as vgg19.npy
2. Download MS COCO dataset - the training script defaults to look for images in a directory named input_images
3. Run:

$ python train.py --data_dir=/path/to/ms_coco --texture=path/to/source_image.jpg