Arm UNICEF Disaster Vulnerability Challenge
'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='rotate(10)'/%3e%3c/g%3e%3cuse xlink:href='%23c' transform='rotate(20)'/%3e%3c/g%3e%3cuse xlink:href='%23d' transform='rotate(40)'/%3e%3c/g%3e%3cuse xlink:href='%23e' transform='rotate(-80)'/%3e%3c/g%3e%3cpath d='M-225-21.5h450v7.5h-450z'/%3e%3cpath fill='%23339E35' d='M-225 86h450v100h-450z'/%3e%3c/svg%3e)
Helping Malawi
$10 000 USD
Completed (over 2 years ago)
1200 joined
346 active
Start
15 Mar 24
Close
23 Jun 24
Reveal
23 Jun 24
Submission File Question
Help · 7 May 2024, 13:39 · 3
Thank you for any help here! This is my first Object Detection contest and I am currently experimenting with a Pytorch Implimentation of RetinaNet.
Can I treat this as a binary OD problem? ie, encompass all 3 roof types into a single label? Target is the count of detected roofs per imageID in the test set?
image_id Target
id_016450pfgcpy_1 22
id_016450pfgcpy_2 55
id_016450pfgcpy_3 10
Ah- I see now, each image_id has 3 rows, and you must give the counts for each label in the submission!
Yesss, each image comes back 3 times for the 3 different classes. So for image x for example you will count the number of houses labels 0, 1 and 2
Thank you, Bryan!