How was the StyleTransfer model trained for Caffe2?

[jgong5]

I found the model is different from what was proposed form the original StyleTransfer paper: https://arxiv.org/abs/1508.06576

The original model has been implemented with Caffe: https://github.com/fzliu/style-transfer

May I know how did you train these Caffe2 models? Did you transfer the learning of the original paper model to the new Caffe2 model here?