Why add the 3*3*1*1 conv0 layer in the encoder

xunhuang1995 / AdaIN-style

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

https://arxiv.org/abs/1703.06868

MIT License

1.47k stars 192 forks source link

Open diaodeyi opened 3 years ago

diaodeyi commented 3 years ago

Thanks for your great work! I want to know if there any reason for you to add this layer, is there any experiment result?