pose-ae-train
pose-ae-train copied to clipboard
How to handle the regions of people without annotations on COCO and MPII dataset?
Hi @anewell, I would like to ask a question that how to handle the people without annotations on COCO and MPII dataset. Do you think is it affect the training and testing performance? Thanks.
We mask out the crowd areas in COCO as seen here: https://github.com/umich-vl/pose-ae-train/blob/master/task/loss.py#L16