Autore: Petru Dimitriu
Byzantine music is a genre with ancient origins widespread in the Balkan area, with a history of over a millennium. Its specific notation consists of a series of signs called neumes.
Implement an AI model that classifies the neumes in a sequence stored in an image and produces a sequence representing, for each encountered neume, the number of steps accumulated up to the current neume relative to the initial step (considered at the beginning of the sequence).
Each sample image has a size of 48x48 pixels and represents a single sign.
The training dataset (train.csv) contains the following fields:
Path – the relative path to the sample image.
Effect – the label applied to the image. It can be:
A or B) for neumes without pitch value (the pitch remains unchanged).Example (CSV):
| Path | Effect |
|---|---|
| images/neuma1.png | 1 |
| images/neuma2.png | -2 |
| images/neuma3.png | A |
The evaluation dataset (test.csv) contains two fields:
subtaskID – always 1datapointID – the relative path to the image representing the neume sequenceDetails:
The output file (submission.csv) must contain 3 fields:
subtaskID – always 1datapointID – the relative path to the sequence imageanswer – the recognized sequence, as integers separated by |, each number representing the accumulated relative distance from the initial stepExample:
Neume sequence:
Individual tonal meaning: 1, -2, 1, 1, 1, -1, none, 1, -1, -1
Output file:
| subtaskID | datapointID | answer |
|---|---|---|
| 1 | images/seq1.png | 1|-1|0|1|2|1|1|2|1|0 |
Example:
1|2|0|0|11|2|0|2|3Final score: the ratio between the total score obtained and the maximum possible score (3354), expressed as a percentage, rounded up to the nearest whole number.