VGGConvolutionDenseBlock¶
-
class
maze.perception.blocks.joint_blocks.vgg_conv_dense.
VGGConvolutionDenseBlock
(*args: Any, **kwargs: Any)¶ A block containing multiple subsequent vgg style convolution stacks followed by flattening and a dense layer block.
For details on the convolution part see
VGGConvolutionBlock
. For details on flattening seeFlattenBlock
. For details on dense layers seeDenseBlock
.- Parameters
in_keys – One key identifying the input tensors.
out_keys – One key identifying the output tensors.
in_shapes – List of input shapes.
hidden_channels – List containing the number of hidden channels for hidden layers.
hidden_units – List containing the number of hidden units for hidden layers.
non_lin – The non-linearity to apply after each layer.
-
forward
(block_input: Dict[str, torch.Tensor]) → Dict[str, torch.Tensor]¶ (overrides
PerceptionBlock
)implementation of
ShapeNormalizationBlock
interface