# 1416th place solution + alpha

Congrats all the winners and thanks for sharing solutions!
I was shock down -1356th places, which means my model was good for seen classes but totally failed to predict unseen combinations.
By reference to winners solution I fixed my models, finally it achieved public 0.9925 / private 0.9552.
And this is trained only on TPU and using keras, so it may be useful for someone who want to use TPU and keras user.
[https://www.kaggle.com/bamps53/private0-9552-tpu-keras-metric-learning](https://www.kaggle.com/bamps53/private0-9552-tpu-keras-metric-learning)
| No | model                                | cv    | public | private | rank   |
|----|--------------------------------------|-------|--------|---------|--------|
| 1  | decode 1292 unique labels (original) | 0.999 | 0.9870 | 0.9035  | 1416th |
| 2  | 3 heads for each r, v, c             |       | 0.9891 | 0.9228  | 639th  |
| 3  | 3 models for each r, v, c            |       | 0.9665 | 0.9383  | 56th   |
| 4  | seen: No.1 unseen: No.3              |       | 0.9925 | 0.9552  | 8th    |
| 5  | No.4 with postprocess              |       | 0.9941 | 0.9704  | 2nd    |