File descriptions
train_data.csv
- the training data
train_target.csv
- the corresponding training targets
test_data.csv
- the testing data
sample-submission.csv
- a sample submission file in the correct format
The data has been randomly separated into two parts: training set and testing set. The training set consists of 16,175 examples for you to build your model. The test set consists of 3,965 examples which will be used to determine your score.
Please note:
1. The provided csv files have no index column and header row.
2. In "train_data.csv" and "test_data.csv", each row contains 2304 pixel values (as each face image is of size 48*48 in pixels).
3. "train_target.csv" stores the corresponding target to each row data in "train_data.csv" (0-Angry, 1-Happy, and 2-Neutral).
4. When you save your predictions into a csv file, please follow the submission file format as shown in "Evaluation" section (the submission file requires the specific index column and header row, where the "Id" is a zero-based index corresponding to the order of testing data in the "test_data.csv" file).