The participants will be ranked based on the accuracy of their predictions. The evaluation metric for this competition is the prediction accuracy,
i.e.,
, the proportion of 10-second test recordings for which your algorithm makes the correct prediction.
Submission Format
Submission files should be in csv format and contain two columns: Id and Prediction. The first column of the csv file is the test sample ID (0,1,2,3,...,1499) and the second column is the class name predicted for that sample by your algorithm.
The file should contain a header and have the following format:
Id,Scene_label
0,cafe/restaurant
1,grocery store
2,beach
...
1499,restaurant