Pytorch implementation of the ECCV 2016 paper "Stacked Hourglass Networks for Human Pose Estimation"
BSD 3-Clause "New" or "Revised" License
465
stars
94
forks
source link
Why use 300 training set images when testing #23
Closed
jinchengll closed 3 years ago
In the code of test.py, 300 training set data is used, so will the result be false?