# Private score 90.14 ( gold ) solution

Congratulations to all those who moved up by miles to get into Medal positions, rest who got affected by shake up its always a learning at end of day.
Just for those who wish to find out the solution to get to 90.1 score on private lb. Still to know how near is 90.1 was to gold place.
[https://www.kaggle.com/jaideepvalani/with-b4-pytorch-efficientnet-baseline?scriptVersionId=54134057](https://www.kaggle.com/jaideepvalani/with-b4-pytorch-efficientnet-baseline?scriptVersionId=54134057)
Above is note book.
Below is our solution outline
1)Ensemble models
a) B4 Fastai- Trained using Label Smoothing cross Entropy  EPS 0.35
b) Resnext IBN/Resnext101 /ViT- Trained using Tempered Softmax loss(BiT)
Thanks to my team mate
[@cswwp347724](https://www.kaggle.com/cswwp347724)
for these models
and also
[@rohitsingh9990](https://www.kaggle.com/rohitsingh9990)
for putting very hard efforts  to help us reach 90.7 at lastday
Its sad that we couldnt select our best submission even though there was second thought about selecting a conservative Public LB score. But never mind we are fortunate that we are still in silver.
Our all models were trained using similar methodology.
I was hoping for
[@mobassir](https://www.kaggle.com/mobassir)
and
[@cdeotte](https://www.kaggle.com/cdeotte)
team to have stayed at winning position or atleast in gold, but its always a good learning at the end of every competition.
Well done you guys  !