Goal
It is your job to predict the correct label of the traffic sign. For each Id in the test set, you must predict the label of the German traffic sign image.
Metric
Submissions are evaluated on
[Multi-class-loss](http://wiki.fast.ai/index.php/Log_Loss)
between the predicted onehot values and the observed onehot values
Submission file format
The file should contain a header and have the following format:
id	oh_0    oh_1   oh_2 ... oh_41  oh_42
0	0          0        1       ...   0         0
1	0          1         0      ...   0         0
2	1          0        0      ...   0         0
NOTE:
Ignore or remove the column named Unnamed: 0 in the test data.
Once you create a dataframe containing labels column, name the index column 'id'
Sample code to do this --> data_frame_sol.index.name = 'id'
Please submit the submissions file name as 'sample.csv' to get evaluated.