PytorchGeometricTutorial icon indicating copy to clipboard operation
PytorchGeometricTutorial copied to clipboard

Tutorial 3 - redundant dropout

Open hananell opened this issue 1 year ago • 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?

hananell avatar Oct 30 '23 19:10 hananell