qonnx.transformation.general (module)

class qonnx.transformation.general.ApplyConfig(config)

Bases: qonnx.transformation.base.Transformation

Applies node properties (attributes) from either a config dict or its JSON representation given as a filename. The JSON file can specify default values for particular op_types, as well as values for nodes with particular names. Example dict:

{
# set kernel_size = 3 for all nodes with op_type=Im2Col
"Defaults" : {"kernel_size" : [3, ["Im2Col"]]},
# set kernel_size = 7 for the particular node with name Im2Col_0
"Im2Col_0" : {"kernel_size" : 7}
}

apply(model)

class qonnx.transformation.general.ConvertDivToMul

Bases: qonnx.transformation.base.Transformation

Convert divide by constant nodes to multiply by constant nodes.

apply(model)

class qonnx.transformation.general.ConvertSubToAdd

Bases: qonnx.transformation.base.Transformation

Convert subtract-a-constant nodes to add-a-constant nodes.

apply(model)

class qonnx.transformation.general.GiveRandomTensorNames

Bases: qonnx.transformation.base.Transformation

Give random tensor names to all tensors.

apply(model)

class qonnx.transformation.general.GiveReadableTensorNames

Bases: qonnx.transformation.base.Transformation

Give more human-readable names to all internal tensors. You should apply GiveUniqueNodeNames prior to this transform to avoid empty node names, as the readable names are based on the node names.

apply(model)

class qonnx.transformation.general.GiveUniqueNodeNames(prefix='')

Bases: qonnx.transformation.base.Transformation

Give unique names to each node in the graph using enumeration, starting with given prefix (if specified in the constructor).

apply(model)

class qonnx.transformation.general.GiveUniqueParameterTensors

Bases: qonnx.transformation.base.Transformation

Make every parameter tensor unique. The aim is to avoid affecting other nodes apart from the one the system is currently operating on.

apply(model)

class qonnx.transformation.general.RemoveStaticGraphInputs

Bases: qonnx.transformation.base.Transformation

Remove any top-level graph inputs that have initializers.

apply(model)

class qonnx.transformation.general.RemoveUnusedTensors

Bases: qonnx.transformation.base.Transformation

Remove any unused tensors in the graph by removing any initializers, ValueInfo and tensor annotations associated with it. Unused tensors do not appear as any input/output for any graph nodes.

apply(model)

class qonnx.transformation.general.SortGraph

Bases: qonnx.transformation.base.Transformation

Returns the model with its node list sorted topologically. Any ONNX graph to be executed must have a topologically sorted node list, as dictated by the ONNX standard.

apply(model)