Evaluation results are always zero

hellojialee / Improved-Body-Parts

Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

https://arxiv.org/abs/1911.10529

258 stars 42 forks source link

Evaluation results are always zero #36

Closed aravindsairam closed 3 years ago

aravindsairam commented 3 years ago

Average precision and average recall from evaluate.py always give zero.

Screenshot 2021-01-10 at 11 43 27

I am using images of size 512(other parameters are default as it is), I have trained the model without checkpoint and for 20 epochs with COCO dataset. The results were decent. But evaluation is zero(evaluation on validation set for 50 ids). What would be the reason ?

Thanks, Aravind

hellojialee commented 3 years ago

Hi @aravindsairam I suggest you run demo_image.py to check that the output or the file format is correct.

stale[bot] commented 3 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.