AntonioLonga/PytorchGeometricTutorial

Tutorial 3 - redundant dropout

hananell opened this issue · 0 comments

Hi

In the final GAT implementation:
We use two imported GATConv layers.
In the constructor, we initialize each one of them with a dropout of 0.6.
In the forward method, we apply additional dropout before each one of them.
What's the point in doing additional dropout?