Why the AP is always 0?

[Yinhance]

 $ ~/MSPN/exps/mspn.2xstg.coco$ python -m torch.distributed.launch --nproc_per_node=1 test.py -i 10000
loading annotations into memory...
Done (t=5.33s)
creating index...
index created!
2760/2760 [19:29<00:00,  2.36it/s]
2021-04-05 12:39:01 deepserver3 COCO[11713] INFO Accumulating ...
2021-04-05 12:39:01 deepserver3 COCO[11713] INFO Dumping results ...
2021-04-05 12:39:06 deepserver3 COCO[11713] INFO Get all results.
Loading and preparing results...
DONE (t=3.67s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *keypoints*
DONE (t=9.53s).
Accumulating evaluation results...
DONE (t=0.33s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets= 20 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets= 20 ] = 0.000
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets= 20 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 20 ] = 0.001
 Average Recall     (AR) @[ IoU=0.50      | area=   all | maxDets= 20 ] = 0.002
 Average Recall     (AR) @[ IoU=0.75      | area=   all | maxDets= 20 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.001

[Whj-cv]

I have the same problem. Have you solved it？

[Yinhance]

I have the same problem. Have you solved it？

Not yet :(

[yuy01]

I also met this prolem, have anyone solved this problem?