How to handle the regions of people without annotations on COCO and MPII dataset?

princeton-vl / pose-ae-train

Training code for "Associative Embedding: End-to-End Learning for Joint Detection and Grouping"

BSD 3-Clause "New" or "Revised" License

373 stars 76 forks source link

How to handle the regions of people without annotations on COCO and MPII dataset? #9

Open yw155 opened 6 years ago

yw155 commented 6 years ago

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.

anewell commented 6 years ago

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