gluonts.mx.block.mlp module#
- class gluonts.mx.block.mlp.MLP(layer_sizes: List[int], flatten: bool, activation='relu')[source]#
Bases:
HybridBlock
Defines an MLP block.
- Parameters:
layer_sizes – number of hidden units per layer.
flatten – toggle whether to flatten the output tensor.
activation – activation function of the MLP, default is relu.