For each ID (or name of the image) in the test set, you must predict the corresponding class. The submission file should be a CSV having the following format (header must be included):

The header should be the text written except the brackets.

    ID(name of the image),Class(number of image)
    image a,0
    image b,1
    image c,2
    image d,3
    image e,4
    image f,5
    image g,6

Here, the numbers correspond to the classes in the same order as they are given in the ground truth file, which is:
0 - MEL
1 - NV
2 - BCC
3 - AKIEC
4 - BKL
5 - DF
6 - VASC