search

garyzhao / SemGCN

The Pytorch implementation for "Semantic Graph Convolutional Networks for 3D Human Pose Regression" (CVPR 2019).
https://arxiv.org/abs/1904.03345
Apache License 2.0
465 stars 78 forks source link

Questions about feature dimensions #52

Open YLAKK opened 2 years ago

YLAKK commented 2 years ago

Hi，I have a question, why is the dimension in the first SemGCN module and residual block set to 128? What is the impact of this dimension change on feature extraction?I only know that the output feature dimension should be set to 3.