Question about categories
byminji opened this issue · comments
Hi,
Thank you for your great work.
I have two questions about the category setting of the model.
-
I have noticed that the categories (classes) in KAIST-RGBT dataset annotation are ['ignore', 'person', 'cyclist', 'people', 'person?'], but the number of categories in the config file is set to three. What exactly does each category id mean in the model?
-
If my understanding is correct, the evaluation script converts the predicted result into a json format for submission to the evaluation server, where all the predictions are made to have a category_id of 1. Are the results of the model's detection considered as only one category because all the classes predicted by the model are sub-categories of 'pedestrian'?
Thank you.
Thank you for your interest in our work.
-
We follow this comment, so we Integrate all the classes into 'person' without 'ignore'. And the meaning of 'number of categories' in the config file is ['ignore', 'visible only', 'thermal only'] and that is the condtribution of our paper. Please refer to our paper for more detailed information. link
-
Yes.
If you want to know more details about our paper, please refer to our paper for more detailed information. link.
Thanks for your quick reply:) 감사합니다!
Feel free to send me a quick e-mail if you have more questions. 감사합니다.