The evaluation metric for this competition is classification accuracy, i.e., the percentage
of species you correctly identify.
Submission Format
Submission files should contain two columns: Id and Category (the predicted category for that image). The file should contain a header and have the format described below. Id represents the number of the test example, ranging from 0 to 999. The prediction is the corresponding label, between 0 and 9. The Ids correspond to the file names in the test set.  The correspondence between the category labels and ImageNet categories may be found in the file class_to_idx.json.
The file should contain a header and have the following format:
Id,Category
0,1