# My Solution with Code (Public LB 45.6)

Thank you for all the participants in this competition.
I provide my solution that gets 45.6 in public LB.
Solution
My refactored code is available at
[https://github.com/fujibo/kaggle-dog](https://github.com/fujibo/kaggle-dog)
.
My code is based on SN-GAN with projection discriminator
[https://github.com/pfnet-research/sngan_projection](https://github.com/pfnet-research/sngan_projection)
.
I add the following modifications to the base code.
- Apply spectral normalization to the generator
- Increase the learning rate and reduce the number of critics of the discriminator
These techniques are used in SA-GAN, which outperforms SN-GAN.
I did not use the original SA-GAN code because I am not good at tensorflow.
Moreover, I tuned hyper-parameters as follows.
- change
batch size
from 64 to 128
- change
iteration_decay_start
from 0 to 18000
- change
iteration
to 24000
Insights
For reducing training time, I produced dog images with 32x32 pixels followed by bilinear resizing, but obtained a worse score.
Different trials have different training time somehow, that is, trial A cannot finish 27000 iterations, while trial B can finish 28000 iterations.