OMLT Layers

Neural network layer classes.

class omlt.neuralnet.layer.ConvLayer(input_size, output_size, strides, kernel, *, activation=None, input_index_mapper=None)[source]

Bases: omlt.neuralnet.layer.Layer

Two-dimensional convolutional layer.

Parameters

  • input_size (tuple) – the size of the input.

  • output_size (tuple) – the size of the output.

  • strides (matrix-like) – stride of the cross-correlation kernel.

  • kernel (matrix-like) – the cross-correlation kernel.

  • activation (str or None) – activation function name

  • input_index_mapper (IndexMapper or None) – map indexes from this layer index to the input layer index size

property kernel
property kernel_shape
kernel_with_input_indexes(out_d, out_r, out_c)[source]

Returns an iterator over the kernel value and input index for the output at index (out_d, out_r, out_c).

Parameters

  • out_d (int) – the output depth.

  • out_d – the output row.

  • out_c (int) – the output column.

property strides
class omlt.neuralnet.layer.DenseLayer(input_size, output_size, weights, biases, *, activation=None, input_index_mapper=None)[source]

Bases: omlt.neuralnet.layer.Layer

Dense layer implementing output = activation(dot(input, weights) + biases).

Parameters

  • input_size (tuple) – the size of the input.

  • output_size (tuple) – the size of the output.

  • weight (matrix-like) – the weight matrix.

  • biases (array-like) – the biases.

  • activation (str or None) – activation function name

  • input_index_mapper (IndexMapper or None) – map indexes from this layer index to the input layer index size

property biases
property weights
class omlt.neuralnet.layer.IndexMapper(input_size, output_size)[source]

Bases: object

Map indexes from one layer to the other.

Parameters

  • input_size (tuple) – the input size

  • output_size (tuple) – the mapped input layer’s output size

property input_size
property output_size
class omlt.neuralnet.layer.InputLayer(size)[source]

Bases: omlt.neuralnet.layer.Layer

The first layer in any network.

Parameters

size (tuple) – the size of the input.

class omlt.neuralnet.layer.Layer(input_size, output_size, *, activation=None, input_index_mapper=None)[source]

Bases: object

Base layer class.

Parameters

  • input_size (tuple) – size of the layer input

  • output_size (tuple) – size of the layer output

  • activation (str or None) – activation function name

  • input_index_mapper (IndexMapper or None) – map indexes from this layer index to the input layer index size

property activation

Return the activation function

eval(x)[source]

Evaluate the layer at x.

Parameters

x (array-like) – the input tensor. Must have size self.input_size.

property input_index_mapper

Return the index mapper

property input_indexes

Return a list of the input indexes

property input_indexes_with_input_layer_indexes

Return an iterator generating a tuple of local and input indexes.

Local indexes are indexes over the elements of the current layer. Input indexes are indexes over the elements of the previous layer.

property input_size

Return the size of the input tensor

property output_indexes

Return a list of the output indexes

property output_size

Return the size of the output tensor