Replies: 1 comment 1 reply
-
See https://www.ccoderun.ca/programming/darknet_faq/#negative_samples and https://www.ccoderun.ca/programming/darknet_faq/#image_markup |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I have an object detection project of two classes (person, animal), and I want to use darknet/yolov4 for it. The images can contain person(s) and/or animal(s), or none of these classes. For example, an image may just contain cars and I don't need to detect these cars.
My question is how do I handle the annotation file for this image that contains no object of interest? Do I create an annotation file for it and its content is empty?
Beta Was this translation helpful? Give feedback.
All reactions