An implementation of neural style in TensorFlow.
TensorFlow doesn't support L-BFGS (which is what the original authors used), so we use Adam. This may require a little bit more hyperparameter tuning to get nice results.
See here for an implementation of fast (feed-forward) neural style in TensorFlow.
Pre-trained VGG network(vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5), put it into /Users/YOURNAME/.keras/models, or specify its location using the--networkoption.
You can install Python dependencies using pip install -r requirements.txt, and it should just work. If you want to install the packages manually, here's a list:
python neural_style_transfer.py "<content file>" "<style file>" "<output file>"
<output file>no extension is required.
Run python neural_style.py --help to see a list of all options.
Use --checkpoint-output and --checkpoint-iterations to save checkpoint images.
Copyright (c) 2015-2017 Wanguy. Released under GPLv3. See LICENSE.txt for details.