A tensorflow implementation of a Learned Representation of artistic style

Most of the code in the repo was taken from hwalsuklee/tensorflow-fast-style-transfer.

This is the implementation used in my app Spectrum - Artistic Photo editor. If this fork helps you, please consider downloading the app, it really helps me out.

1. Added Conditional Instance Normalization which enables a single model to learn multiple styles with only a few extra parameters.
2. Used Upsampling+Convolution instead of Transpose Convolutions(prevents checkerboard artifacts).
3. Experimented with Depthwise separable convolutions instead of regular convolutions. The current model still uses all convolutional layers but you can replace _conv_layer with _depthwise_conv_layer for some layers to reduce the model size(but don't do this for the initial layers).

I trained my models in this Kaggle kernel. Please see run_train.py and run_test.py for training options.

Spectrum Landing Page