Please download the file submissionFileFormat.csv from the data page. This file lists the points whose locations need to be detected.
Submission File Columns
Row Id:
integer id for the row
Image Id:
integer id for the image. There are 1783 images in the test set.
Feature Name:
string identifying the facial keypoint, e.g., left_eye_center_x, left_eye_center_y, mouth_bottom_center_lip_x, nose_tip_y
Location:
x- or y-coordinate of the specified feature.
This is the value to be predicted.
Note that you will not be detecting all 30 features (x and y coordinates for 15 facial keypoints) for each image. Some images require fewer keypoints to be detected. Please see submissionFileFormat.csv for the details.