YOLO-World
YOLO-World copied to clipboard
How to modify the size of the vocabulary during training ?
Hello, thank you for coming up with such a great job. For the content in section 3.2 of this paper:
Training with Online Vocabulary ... The vocabulary for each mosaic sample contains at most M nouns, and M is set to 80 as default.
I understand that it means M is set to 80 for all datasets, e.g.,object365, coco and LVIS dataset.
but how should I adjust the size of this value? When I have customized dataset that needs to be trained, how should I adjust the size of this value, and what will be the impact of adjusting the size of this value?