True excellent work, but in the configuration file, stage3 and STAG4 NUM_MODULES are both 1, I think it should be 4 and 3, corresponding to the paper. I'm looking forward to your reply

HRNet / HRNet-Object-Detection

Object detection with multi-level representations generated from deep high-resolution representation learning (HRNetV2h). This is an official implementation for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919

Apache License 2.0

644 stars 97 forks source link

True excellent work, but in the configuration file, stage3 and STAG4 NUM_MODULES are both 1, I think it should be 4 and 3, corresponding to the paper. I'm looking forward to your reply #50

Open shui-tian-ju-shi opened 2 years ago

shui-tian-ju-shi commented 2 years ago

'POSE_HIGH_RESOLUTION_NET.STAGE3.NUM_MODULES = 1' 'POSE_HIGH_RESOLUTION_NET.STAGE4.NUM_MODULES = 1' In this case ,wouldn't every stage has only one block? Instead of your corresponding 1,4,3