search

ZheC / Realtime_Multi-Person_Pose_Estimation

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)
Other
5.09k stars 1.37k forks source link

Are you using a test set, during training? #65

Open priyapaul opened 7 years ago

priyapaul commented 7 years ago

May be it is so silly, I see the following code, where you skip all the validation set. But you add validation images to the training set in getAnno. So it is just to increase the size of your training data ? And why dont you use a test set? Thank you very much in advance! 

if (data[idx]['isValidation'] != 0 and validation == 1):
            print '%d/%d skipped' % (count,idx)
            continue
ZheC commented 7 years ago

Yes, we have a small validation set during training. It is different with the COCO val set. For more details, please refer the code in https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/blob/master/training/genJSON.m#L36