# 8th place solution(private 89)

code
kernel
[https://www.kaggle.com/katotetsuro/stylegan-private-89?scriptVersionId=18524688](https://www.kaggle.com/katotetsuro/stylegan-private-89?scriptVersionId=18524688)
github
[https://github.com/katotetsuro/chainer-stylegan/tree/ac](https://github.com/katotetsuro/chainer-stylegan/tree/ac)
FYI: This scripting style is borrowed from this:
[https://github.com/lopuhin/kaggle-script-template](https://github.com/lopuhin/kaggle-script-template)
I prefer script style, which is easy to manage by git.
summary
To be honest, there is no special technique in my solution.
I chose stylegan, then looked for good parameters.
My stylegan starts with public score 140, then tuning parameters, I got 35.
for preprocessing: crop image by bounding box, random horizontal flip
reduce input channel size of style generator to 256 because of resource limitation.
all hyper parameters are shown in below.
[https://github.com/katotetsuro/chainer-stylegan/blob/ac/src/stylegan/config.py](https://github.com/katotetsuro/chainer-stylegan/blob/ac/src/stylegan/config.py)
[https://github.com/katotetsuro/chainer-stylegan/blob/ac/script_template.py](https://github.com/katotetsuro/chainer-stylegan/blob/ac/script_template.py)
trials that didn't work for me
Truncation trick from stylegan paper. I tried various truncation strength, but without truncation was the best.
Auxiliary Classifier
Data cleaning. I thought training data quality is quite important, so I did some procedure (dog face detection, manually picking good images..) but nothing worked.
Today, I read some kernels and learned  there's some good techniques.
This is one of the room for improvement of my solution, I guess.
It was really fun competition! Thanks for kaggle team!!