Submissions are evaluated using the multi-class logarithmic loss. Each image has been labeled with one true class. For each image, you must submit a set of predicted probabilities (one for every class). The formula is then,
$$log loss = -\frac{1}{N}\sum_{i=1}^N\sum_{j=1}^My_{ij}\log(p_{ij}),$$
where N is the number of images in the test set, M is the number of class labels, \\(log\\) is the natural logarithm, \\(y_{ij}\\) is 1 if observation \\(i\\) is in class \\(j\\) and 0 otherwise, and \\(p_{ij}\\) is the predicted probability that observation \\(i\\) belongs to class \\(j\\).
The submitted probabilities for a given image are not required to sum to one because they are rescaled prior to being scored (each row is divided by the row sum). In order to avoid the extremes of the log function, predicted probabilities are replaced with \\(max(min(p,1-10^{-15}),10^{-15})\\).
Submission Format
You must submit a csv file with the image name, all candidate class names, and a probability for each class. The order of the rows does not matter. The file must have a header and should look like the following:
image,acantharia_protist_big_center,...,unknown_unclassified
1.jpg,0.00826446,...,0.00826446
10.jpg,0.00826446,...,0.00826446
...
etc.