### There are two baselines at **Leaderboard** tab. 

![baselines](https://i.imgur.com/75ZSsrC.png)

### 1. **Baseline(100%)**
The score results from trained model with 40,551 labeled dataset. (whole train dataset)
Model : CNN in model.py file

### 2. **Baseline(10%)**
The score results from trained model with 10% labeled dataset over whole train dataset. 
Model : CNN in model.py file

Those two baselines use hyper-parameters as below.
![params](https://i.imgur.com/gewatbq.png)