module `testing.einsum.einsum_impl_classes`#

Short summary#

module mlprodict.testing.einsum.einsum_impl_classes

Classes representing the sequence of matrix operations to implement einsum computation.

Classes#

class	truncated documentation
`EinsumSubOp`	Defines a sub operation used in Einsum decomposition.
`GraphEinsumSubOp`	Class gathering all nodes produced to explicit einsum operators.

Functions#

function	truncated documentation
`single_axes`	axes contains positive values, then it is the position of this axis in the original matrix, otherwise it is -1 …

Methods#

method	truncated documentation
`__init__`
`__init__`
`__iter__`	Iterates on nodes.
`__repr__`
`_apply_batch_dot`
`_apply_diagonal`
`_apply_expand_dims`
`_apply_id`
`_apply_matmul`
`_apply_mul`
`_apply_reduce_sum`
`_apply_reduce_sum_mm`
`_apply_squeeze`
`_apply_transpose`
`_apply_transpose_mm`
`_check_`
`_check_arg_`
`_check_inputs_`
`_check_onnx_opset_`
`_check_row_`	Checks input or output is valid.
`_check_shape_`
`_compute_output_row_batch_dot`
`_compute_output_row_diagonal`
`_compute_output_row_expand_dims`
`_compute_output_row_id`
`_compute_output_row_matmul`
`_compute_output_row_mul`
`_compute_output_row_reduce_sum`
`_compute_output_row_reduce_sum_mm`
`_compute_output_row_squeeze`
`_compute_output_row_transpose`
`_compute_output_row_transpose_mm`
`_get_data`
`_get_forward_nodes`	Returns the forward nodes.
`_onnx_name`
`_pprint_forward`
`_replace_node_sequence`	Removes a sequence of nodes. The method does not check that the graph remains consistent.
`_to_onnx_batch_dot`
`_to_onnx_expand_dims`
`_to_onnx_id`
`_to_onnx_mul`
`_to_onnx_reduce_sum`
`_to_onnx_squeeze`
`_to_onnx_transpose`
`add_info`	Adds information to the node.
`append`	Adds one input or result.
`apply`	Applies one operator on the data.
`apply_sequence`	Applies a sequence of operations on a list of inputs.
`clean_unused_nodes`	Cleans nodes with unused outputs.
`compute_output_row`	Updates row based on the operator.
`dot_label`	Displays some informations useful to understand the operator.
`get_dot_kind`	Every matrix multiplication can be either:
`mark`	Marks one input or result as an intermediate result after a full einsum step.
`mark_last_node`	Marks the last node as the final output.
`remove_duplicate_transpose`	Removes consecutive transpose by merging them.
`simplify_mm_nodes`	Node name suffixed by mm are an artifact to keep the graph consistent while building it. They can now …
`to_dot`	Produces a graph in dot.
`to_onnx`	Converts this node into ONNX. Enumerates all ONNX node which participate to the conversion. The last one …
`to_onnx`	Converts the graph into ONNX.

Documentation#

Classes representing the sequence of matrix operations to implement einsum computation.

source on GitHub

class mlprodict.testing.einsum.einsum_impl_classes.EinsumSubOp(full_dim, name, *inputs, **kwargs)#

Bases: object

Defines a sub operation used in Einsum decomposition.

Parameters:

name – name (reshape, transpose, reduce_sum, matmul, id, squeeze, diagonal, mul, batch_dot)
inputs – inputs
kwargs – arguments

Operator suffixed by _mm (transpose_mm, reduce_sum_mm) are equivalent to the same operator without the suffix but takes two inputs and only changes the first one.

Attributes _info summarizes the known information about dimensions. Many of them are empty because inserted. Value 1 means it was the case, 2 means it is a plain dimension.

source on GitHub

__init__(full_dim, name, *inputs, **kwargs)#

__repr__()#: Return repr(self).

_allowed = {'batch_dot', 'diagonal', 'expand_dims', 'id', 'matmul', 'mul', 'reduce_sum', 'reduce_sum_mm', 'squeeze', 'transpose', 'transpose_mm'}#

_apply_batch_dot(data, verbose=False, **kwargs)#

_apply_diagonal(data, verbose=False, **kwargs)#

_apply_expand_dims(data, verbose=False, **kwargs)#

_apply_id(data, verbose=False, **kwargs)#

_apply_matmul(data, verbose=False, **kwargs)#

_apply_mul(data, verbose=False, **kwargs)#

_apply_reduce_sum(data, verbose=False, **kwargs)#

_apply_reduce_sum_mm(data, verbose=False, **kwargs)#

_apply_squeeze(data, verbose=False, **kwargs)#

_apply_transpose(data, verbose=False, **kwargs)#

_apply_transpose_mm(data, verbose=False, **kwargs)#

_check_()#

_check_arg_(name, typ, empty=False)#

_check_inputs_(n_expected, check_dim=False)#

_check_onnx_opset_(opset, limit)#

_check_row_(row, inp=False, verbose=False)#

Checks input or output is valid.

source on GitHub

_check_shape_(m)#

_compute_output_row_batch_dot(row, row2=None, ab=False, verbose=False)#

_compute_output_row_diagonal(row, row2=None, ab=False, verbose=False)#

_compute_output_row_expand_dims(row, row2=None, ab=False, verbose=False)#

_compute_output_row_id(row, row2=None, ab=False, verbose=False)#

_compute_output_row_matmul(row, row2=None, ab=False, verbose=False)#

_compute_output_row_mul(row, row2=None, ab=False, verbose=False)#

_compute_output_row_reduce_sum(row, row2=None, ab=False, verbose=False)#

_compute_output_row_reduce_sum_mm(row, row2=None, ab=False, verbose=False)#

_compute_output_row_squeeze(row, row2=None, ab=False, verbose=False)#

_compute_output_row_transpose(row, row2=None, ab=False, verbose=False)#

_compute_output_row_transpose_mm(row, row2=None, ab=False, verbose=False)#

_get_data(data, key)#

_onnx_name()#

_to_onnx_batch_dot(names, opset, verbose=False, **kwargs)#

_to_onnx_expand_dims(names, opset, verbose=False, **kwargs)#

_to_onnx_id(names, opset, verbose=False, **kwargs)#

_to_onnx_mul(data, verbose=False, **kwargs)#

_to_onnx_reduce_sum(names, opset, verbose=False, **kwargs)#

_to_onnx_squeeze(names, opset, verbose=False, **kwargs)#

_to_onnx_transpose(names, opset, verbose=False, **kwargs)#

add_info(**kwargs)#

Adds information to the node.

Parameters:: kwargs – dictionary

source on GitHub

apply(data, verbose=False, **kwargs)#

Applies one operator on the data.

Parameters:

data – dictionary storing the results
verbose – prints out intermediate results
kwargs – additional parameters, see methods _apply*

Returns:

output

Known additional paramaters:

‘matmul_impl’: if None calls numpy.einsum through numpy_extended_dot (default) or ‘py’ to call numpy_extended_dot_python instead.

source on GitHub

compute_output_row(row, row2=None, ab=False, verbose=False)#

Updates row based on the operator.

source on GitHub

dot_label()#

Displays some informations useful to understand the operator.

source on GitHub

get_dot_kind()#

Every matrix multiplication can be either:

a simple multiplication (M) (undetected)
a 2D matrix multiplication (11)
a broadcasted matrix multiplication (N1 or 1N)
a batch matrix multiplication (NN)

This method returns which kind it is.

source on GitHub

to_onnx(names, opset=None, verbose=False, **kwargs)#

Converts this node into ONNX. Enumerates all ONNX node which participate to the conversion. The last one is the final output.

Parameters:

names – dictionary where to find already converted name
opset – opset
verbose – prints out intermediate results
kwargs – additional parameter for the conversion

Returns:

output

source on GitHub

class mlprodict.testing.einsum.einsum_impl_classes.GraphEinsumSubOp(letters, mat, lengths, duplicates)#

Bases: object

Class gathering all nodes produced to explicit einsum operators.

Parameters:

letters – list of distinct letters
mat – matrix, see analyse_einsum_equation
lengths – lengths of every input
duplicates – see analyse_einsum_equation

source on GitHub

__init__(letters, mat, lengths, duplicates)#

__iter__()#: Iterates on nodes.

_get_forward_nodes()#

Returns the forward nodes.

source on GitHub

_pprint_forward()#

_replace_node_sequence(added, deleted)#

Removes a sequence of nodes. The method does not check that the graph remains consistent.

source on GitHub

append(op)#

Adds one input or result.

Parameters:: op – integer (an input) or an instance of EinsumSubOp.
Returns:: op or None if op is an integer

source on GitHub

apply_sequence(*inputs, verbose=False, **kwargs)#

Applies a sequence of operations on a list of inputs.

Parameters:

inputs – inputs:
verbose – prints out intermediate results
kwargs – additional parameters, see apply.

Returns:

output

source on GitHub

clean_unused_nodes(verbose=False)#

Cleans nodes with unused outputs.

Parameters:: verbose – display intermediate information

source on GitHub

mark(i, op)#

Marks one input or result as an intermediate result after a full einsum step.

Parameters:: op – integer (an input) or an instance of EinsumSubOp.

source on GitHub

mark_last_node()#

Marks the last node as the final output.

source on GitHub

remove_duplicate_transpose(verbose=False)#

Removes consecutive transpose by merging them.

Parameters:: verbose – display intermediate information

source on GitHub

simplify_mm_nodes(verbose=False)#

Node name suffixed by mm are an artifact to keep the graph consistent while building it. They can now be replaced by the equivalent node without suffix mm.

Parameters:: verbose – display intermediate information

source on GitHub

to_dot(**kwargs)#

Produces a graph in dot.

Parameters:: kwargs – additional graph option
Returns:: string

source on GitHub

to_onnx(output, *inputs, dtype=None, verbose=False, opset=None, **kwargs)#

Converts the graph into ONNX.

Parameters:

output – output name
inputs – input names
dtype – type used for all operators
opset – desired opset, None for the last one
verbose – display intermediate operators
kwargs – additional parameter to use when building the ONNX graph, list of supported parameters: name, ir_version, producer_name, producer_version, initializer

Returns:

ONNX graph

Not all graphs can be converted into ONNX. Only graphs produced with strategy=’numpy’ can be converted otherwise the following error shows up:

NotImplementedError: to_onnx not implemented for 'matmul'.

source on GitHub

mlprodict.testing.einsum.einsum_impl_classes.single_axes(axes)#

axes contains positive values, then it is the position of this axis in the original matrix, otherwise it is -1 meaning this axis is an added single dimension to align all the dimensions based on the einsum equation.

Parameters:: axes – axes described above
Returns:: list of integer in set {1, 2}, 1 for a single axis, 2 otherwise

source on GitHub

module testing.einsum.einsum_impl_classes#

Short summary#

Classes#

Functions#

Methods#

Documentation#

module `testing.einsum.einsum_impl_classes`#