Tensorflow implementation of the ICCV 2017 Paper Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
You can use the train.py script to train your own model or download my model from here. The normalised VGG-19 model can also be found in this link.
To train the model, you need to download MSCOCO dataset and Wikiart dataset. Some pre-processing measures may need to be taken to delete bad images.
Here are some result images (Left to Right: Content , Style , Result):
Acknowledgments: