MaskedGlobalPoolingBlock

class maze.perception.blocks.general.masked_global_pooling.MaskedGlobalPoolingBlock(*args: Any, **kwargs: Any)

A block applying global pooling with optional masking. Pooling is applied w.r.t. the selected pooling function, the pooling dimension and the optional mask (in_keys[1]).

Parameters:

• in_keys – One key identifying the input tensor, and an optional second one identifying the mask tensor.

• out_keys – One key identifying the output tensors.

• in_shapes – List of input shapes.

• pooling_func – Options: {‘mean’, ‘sum’, ‘max’}.

• pooling_dim – The dimension(s) along which the pooling functions get applied.

forward(block_input: Dict[str, torch.Tensor]) → Dict[str, torch.Tensor]

(overrides PerceptionBlock)

Forward pass through the block, iterating over the first 2 dimensions and pooling the rest in dim=0.

param block_input:

The block’s input dictionary.

return:

The block’s output dictionary.