I am trying to understand the model structure of VoxelNet and got stuck at the first layer...
Could you explain a bit what the effect of this dense layer is? Usually these layers are used at the end of the structure for the classification task like this :
Why did you / the authors use that at the very beginning?
Hi @baudm ,
I am trying to understand the model structure of VoxelNet and got stuck at the first layer...
Could you explain a bit what the effect of this dense layer is? Usually these layers are used at the end of the structure for the classification task like this :
Why did you / the authors use that at the very beginning?