search

wangziren1 / pytorch_pose_proposal_networks

Pytorch implementation of pose proposal networks
MIT License
105 stars 23 forks source link

why w and h need to pow()? #6

Open lunalulu opened 5 years ago

lunalulu commented 5 years ago

When parsing the network output, why are the width and height of key points calculated as follows: output[:, :, :, 4:96:6] = output[:, :, :, 4:96:6].pow(2) * cfg.IMG_SIZE output[:, :, :, 5:96:6] = output[:, :, :, 5:96:6].pow(2) * cfg.IMG_SIZE why not below: output[:, :, :, 4:96:6] = output[:, :, :, 4:96:6] * cfg.IMG_SIZE output[:, :, :, 5:96:6] = output[:, :, :, 5:96:6]* cfg.IMG_SIZE thanks~