# First competition 43.6 public score

Hi
Here is our kernel:
[https://www.kaggle.com/shaygu/t3h-d0g-mak3rz-public-43-fid](https://www.kaggle.com/shaygu/t3h-d0g-mak3rz-public-43-fid)
we specifically attached the version that calculates FID every few epochs, we think it brings more insight into the network and also that's the method we used for optimization .
Our knowledge was very limited walking into this competition, and we joined little more then a month ago, so we decided to start with the best public model and see where it gets us. Our steps along the way are further discussed in the kernel, however, I will briefly touch on the points also here.
Using a lot more parameters for the network, improved our score from 60 to 55. Calculating the FID every few epochs allowed us to observe which network performs better (more consistently),  which lead to ability to introduce cyclic learning rate (efficiently now) and small hyper parameter optimizations got us to ~50. The last big step was changing the weight initialization to a broader distribution (0,0.15-1 instead of the 0,0.02 commonly used) got us to ~46 and from there to 43 its minor optimizations.
It was very interesting competition and we've learned a lot. Hopefully, there will be another GAN competition in the near future.
[@eviatarai](/eviatarai)
[@yogevh](/yogevh)