# 37th Place Solution(And Let's talk about CV and private score)

Since some of the top place solutions are already available, I'm not sure if this note is going to add anything new. Just sharing my experiences. :)
My final LB score is an ensemble of 5 Efficientnet models. Here is the overview:
Preprocessing
:   Only Circle Cropping from
[this](https://www.kaggle.com/tanlikesmath/diabetic-retinopathy-resnet50-binary-cropped)
kernel by
[@tanlikesmath](/tanlikesmath)
Augmentations
: Horizontal and Vertical Flip, 360 rotation, zoom 20%-25%, lighting 50%. Used Fast.ai transformations.
Training
:  Mostly followed
[@drhabib](/drhabib)
's
[method](https://www.kaggle.com/c/aptos2019-blindness-detection/discussion/100815#latest-582005)
. Did 5+10 training using
2015
data as train and
2019
as validation set. Then I split the
2019
data into 80:20 ratio using
sklearn
's Stratified Split function and finetuned the previously trained model over it for 15 epochs. I took the best model based on validation loss which didn't seem to be overfitted and used it for submission. I used a fixed seed so that I can compare different model performances over the same val set. Didn't use CV or TTA.
As
[@rishabhiitbhu](/rishabhiitbhu)
[showed](https://www.kaggle.com/c/aptos2019-blindness-detection/discussion/106844#latest-620958)
that the class distribution is quite similar in different datasets, I had a hunch that it wouldn't be that much different for our large test set. This is why I trusted my stratified validation data(can't even imagine what would have happened if I were wrong).
My Validation and Public scores didn't seem to be correlated but now the private scores resemble my val scores. Here is a summary of the models I used:
| Model           | Image Size | Val Kappa | Public Kappa | Private Kappa |
|-----------------|------------|-----------|--------------|---------------|
| Efficientnet B2 | 256        | 0.922    | 0.807       | 0.918        |
| Efficientnet B1 | 256        | 0.926    | 0.804       | 0.921        |
| Efficientnet B0 | 256        | 0.919    | 0.816       | 0.914        |
| Efficientnet B3 | 256        | 0.921    | 0.812       | 0.917        |
| Efficientnet B5 | 300        | 0.920     | 0.802       | 0.916        |
| Ensemble        |           | 0.932    | 0.826       | 0.926        |
Please share and let us know about your CV and Private scores. Also congratulations to the ones who survived the LB shakeup. :)