GAST-Net-3DPoseEstimation icon indicating copy to clipboard operation
GAST-Net-3DPoseEstimation copied to clipboard

Published 20 hours ago • verified publisher icon fabro66

Question about GAST-Net model

Open z0978916348 opened this issue 3 years ago • 0 comments

Hi! Can you explain why GAST-Net's dimension is (25, 17, 256) (T, N, C) after executing first Graph Attention Block in the paper?  I think input shape (256, 27, 17) will be (256, 9, 17) after going through Conv2D with kernel (3,1) and stride (3, 1) in gast_net.py When I print the residual shape in the network, it shows me (256, 9, 17) # (C, T, N).

Thanks

z0978916348 avatar Jul 07 '21 04:07 z0978916348