search

SilvioGiancola / SoccerNetv2-DevKit

Development Kit for the SoccerNet Challenge
MIT License
168 stars 39 forks source link

Camera Change Detection #3

Closed programmeddeath1 closed 3 years ago

programmeddeath1 commented 3 years ago

Hi, can you tell me how is the labels-camera.json file generated? I am assuming it is generated through inference run by BasicModel-Segmentation. Will it be run from the inference code for Task2-BasicModelSegmentation and if so can it be shared, it seems to be commented in the main.py for task2.

Thank you for your help in advance! This seems to be a very interesting research and your loss function is amazing conceptually and even practically kudos!

meisamjam commented 3 years ago

Hi The label-camera.json files are annotations(ground-truths) that have been manually annotated by people. These ground-truths are then used to train the BasicModel-Segmentation, CALF-segmentation, and CALF-detection and to evaluate the performance of the different models.