Tekijä: Mihai Nan
For this task, you need to implement a model capable of estimating the number of emojis present in an image with a geometric background.
The dataset is provided as images along with associated CSV files:
train.csv: contains examples for training the model
| Column | Type | Description |
|---|---|---|
| SampleID | string | Unique identifier for each example |
| Path | string | Path to the image containing emojis |
| Label | integer | Number of emojis in the image |
test.csv: contains examples for prediction
| Column | Type | Description |
|---|---|---|
| SampleID | string | Unique identifier |
| Path | string | Path to the image containing emojis |
The score for an example is calculated as follows:
The total score is normalized to 100 over all test examples.
The submission file must be a CSV with two columns:
| Column | Type | Description |
|---|---|---|
| SampleID | string | Unique identifier of the row in the test set |
| PredictedLabel | integer | Predicted number of emojis in the image |
submission.csv| SampleID | PredictedLabel |
|---|---|
| test_0 | 3 |
| test_1 | 1 |
| test_2 | 4 |
This image contains 5 emojis.

This image contains 3 emojis.
