hls4ml.model.optimizer.passes package

Submodules

hls4ml.model.optimizer.passes.bn_fuse module

class hls4ml.model.optimizer.passes.bn_fuse.FuseBatchNormalization

Bases: OptimizerPass

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

transform(model, node)

Transformation to apply if matching was successful.

Transform should return a boolean value indicating if the model graph was altered (by adding/removing nodes).

Parameters

• model (ModelGraph) – Model to optimize

• node (Layer) – The matched node in the model graph.

hls4ml.model.optimizer.passes.fuse_biasadd module

class hls4ml.model.optimizer.passes.fuse_biasadd.FuseBiasAdd

Bases: OptimizerPass

Fuses BiasAdd into Dense/Conv2D layer (common in TF models).

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

transform(model, node)

Transformation to apply if matching was successful.

Transform should return a boolean value indicating if the model graph was altered (by adding/removing nodes).

Parameters

• model (ModelGraph) – Model to optimize

• node (Layer) – The matched node in the model graph.

hls4ml.model.optimizer.passes.multi_dense module

class hls4ml.model.optimizer.passes.multi_dense.ReplaceMultidimensionalDenseWithConv

Bases: OptimizerPass

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

transform(model, node)

Transformation to apply if matching was successful.

Transform should return a boolean value indicating if the model graph was altered (by adding/removing nodes).

Parameters

• model (ModelGraph) – Model to optimize

• node (Layer) – The matched node in the model graph.

hls4ml.model.optimizer.passes.nop module

class hls4ml.model.optimizer.passes.nop.EliminateLinearActivation

Bases: OptimizerPass

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

transform(model, node)

Transformation to apply if matching was successful.

Transform should return a boolean value indicating if the model graph was altered (by adding/removing nodes).

Parameters

• model (ModelGraph) – Model to optimize

• node (Layer) – The matched node in the model graph.

hls4ml.model.optimizer.passes.precision_merge module

class hls4ml.model.optimizer.passes.precision_merge.SetPrecisionConcat

Bases: OptimizerPass

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

transform(model, node)

Set concat output precision

hls4ml.model.optimizer.passes.precision_merge.get_concat_type(itype1, itype2)

hls4ml.model.optimizer.passes.qkeras module

class hls4ml.model.optimizer.passes.qkeras.ApplyAlpha(model, name, attributes, inputs, outputs=None)

Bases: BatchNormalization

A custom layer to scale the output of a QDense layer which used ‘alpha != 1’ Inference computation uses BatchNormalization methods

add_bias(bias, quantizer=None)

add_weights(scale, quantizer=None)

initialize()

class hls4ml.model.optimizer.passes.qkeras.ExtractTernaryThreshold

Bases: OptimizerPass

The input value (threshold) at which the output of a a ternary activation changes is configurable. This pass extracts that threshold point, inserting a BatchNormalization layer to execute the scaling. That BatchNormalization layer is then expected to be fused into a BatchNormalizationQuantizedTanh layer configured with the correct threshold.

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

transform(model, node)

Transformation to apply if matching was successful.

Transform should return a boolean value indicating if the model graph was altered (by adding/removing nodes).

Parameters

• model (ModelGraph) – Model to optimize

• node (Layer) – The matched node in the model graph.

class hls4ml.model.optimizer.passes.qkeras.FuseConsecutiveBatchNormalization

Bases: OptimizerPass

OptimizerPass to merge consecutive BatchNormalization layers. These may exist in a model after QKerasFactorizeAlpha layer. Scale and Bias of each layer are combined into scale and bias of a single layer.

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

transform(model, node)

Transformation to apply if matching was successful.

Transform should return a boolean value indicating if the model graph was altered (by adding/removing nodes).

Parameters

• model (ModelGraph) – Model to optimize

• node (Layer) – The matched node in the model graph.

class hls4ml.model.optimizer.passes.qkeras.OutputRoundingSaturationMode

Bases: ConfigurableOptimizerPass

Set the Rounding and Saturation mode of the output (and accumulator, if applicable) of the layers specific in layer list. The layer list is empty by default. To specify which layer to apply this pass to, perform e.g.: hls4ml.model.optimizer.get_optimizer(‘output_rounding_saturation_mode’).configure(layers=[‘Dense’, ‘Activation’]) The Rounding and Saturation modes are ‘None’ by default (so use the compiler defaults) To set which mode to use: hls4ml.model.optimizer.get_optimizer(‘output_rounding_saturation_mode’).configure(rounding_mode=’AP_RND_CONV’) hls4ml.model.optimizer.get_optimizer(‘output_rounding_saturation_mode’).configure(saturation_mode=’AP_SAT’)

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

precision_string_modify(pstr)

transform(model, node)

Transformation to apply if matching was successful.

Transform should return a boolean value indicating if the model graph was altered (by adding/removing nodes).

Parameters

• model (ModelGraph) – Model to optimize

• node (Layer) – The matched node in the model graph.

class hls4ml.model.optimizer.passes.qkeras.QKerasFactorizeAlpha

Bases: OptimizerPass

OptimizerPass for extracting alpha “scale” from QKeras quantized layer. The weights of the Q{Dense, Conv} layer are scaled to the common data type, and an ‘ApplyAlpha’ layer is inserted to reapply the scale.

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

transform(model, node)

Transformation to apply if matching was successful.

Transform should return a boolean value indicating if the model graph was altered (by adding/removing nodes).

Parameters

• model (ModelGraph) – Model to optimize

• node (Layer) – The matched node in the model graph.

class hls4ml.model.optimizer.passes.qkeras.QKerasPO2Quantizer(config)

Bases: object

hls4ml.model.optimizer.passes.qkeras.register_qkeras()

hls4ml.model.optimizer.passes.stamp module

class hls4ml.model.optimizer.passes.stamp.MakeStamp

Bases: ModelOptimizerPass

transform(model)

Transformation to apply if matching was successful.

Transform should return a boolean value indicating if the model graph was altered (by adding/removing nodes).

Parameters

• model (ModelGraph) – Model to optimize

• node (Layer) – The matched node in the model graph.

hls4ml.model.optimizer.passes.transpose_opt module

class hls4ml.model.optimizer.passes.transpose_opt.RemoveUselessTranspose

Bases: OptimizerPass

match(node)

Predicate to match on a given node.

Parameters

node (Layer) – Node in the model graph to try matching the optimizer on.

transform(model, node)

Remove a transpose layer if it doesn’t do anything. i.e 1D input and perm = [0]

Module contents