search

princeton-vl / pose-hg-train

Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"
Other
575 stars 185 forks source link

Using nn.gModule #14

Closed wydges closed 7 years ago

wydges commented 8 years ago

I have another question, I'm new to machine learning, and especially to torch. Why you wrapped your model with nn.gModule, neither than nn.Module. What is the difference?

yangky11 commented 8 years ago

nn.gModule is in a torch package named nngraph, it encapsulates a computational graph into a nn.Module-compatible module on which you can invoke forward and backward . Check out nngraph