8.1.1.2.1.1.1.7. blueoil.converter.core.optimizer
¶
Module of optimization passes.
8.1.1.2.1.1.1.7.1. Module Contents¶
8.1.1.2.1.1.1.7.1.1. Functions¶
|
Removes those nodes of a Graph that satisfies the condition node.op_type() == Identity. |
|
Changes the data order of every node to be NHWC. |
|
Given a node N, if the value of each input of N is known at compilation time then N will be executed. |
|
Given a node N, it will propagate information about quantization into the convolution nodes. |
|
Given a Quantizer node Q: |
|
Given a Quantized convolution node C, it will pack the weights of C into 32 bit words. |
|
Given a convolution node C, if C has proper quantization details, it will mark C as quantized and it will |
|
Further propagate output data types. |
|
Further propagate output data types. |
|
Insert Cast Operator if needed |
|
Lookup. |
|
Simplify BarchNorm operator. |
-
blueoil.converter.core.optimizer.
pass_remove_identities
(graph: Graph) → None¶ Removes those nodes of a Graph that satisfies the condition node.op_type() == Identity.
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_transpose
(graph: Graph) → None¶ - Changes the data order of every node to be NHWC.
The fastest changing dimension is C N stands for batch size (on inference we assume is 1. H and W are the height and width respectively. C stands for channels)
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_constant_folding
(graph: Graph) → None¶ - Given a node N, if the value of each input of N is known at compilation time then N will be executed.
The node N and its inputs will be replaced with a Constant node which holds the computed output of N.
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
processed_nodes (list) – The list of the processed nodes so far.
-
blueoil.converter.core.optimizer.
pass_propagate_quantization_details_into_conv
(graph: Graph) → None¶ Given a node N, it will propagate information about quantization into the convolution nodes.
There are two types of nodes. Those which preserve quantization (for example, Space2Depth because does not affect the actual values of the input data, only changes it positions) and those which destroy quantization (for example, BatchNormalization, because it involves float operations).
If there is path in the Graph which connect a Quantizer node Q to a Conv node C and every node between Q and C preserve quantization (for example, Q -> Space2Depth -> Concat > Conv) then the details about the quantizer Q should be propagated into the convolution node C.
This pass allows us to further process the convolution nodes later and maybe quantize these convolutions based on these quantization details. Note that a convolution node has two inputs, input data and weights. We propagate quantization details through both the input node branch and the weight node branch.
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_compute_thresholds
(graph: Graph) → None¶ - Given a Quantizer node Q:
if there is a backward path between Q and a convolution node and,
every node N of that path satisfies the condition N.is_monotonic and,
the convolution node C (the end of this path) is a quantized convolution
then this pass construct an LUT per channel which maps a possible output value of the quantized convolution node C to the corresponding output of the quantization node Q. This effectively compress the path C -> … -> Q into a list of LUTs that can be used during inference.
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_pack_weights
(graph: Graph) → None¶ - Given a Quantized convolution node C, it will pack the weights of C into 32 bit words.
If the node Q that apply quantization to the weights of C quantizes, for example, into 1 bit values then one 32 bit word will contain 32 weights.
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_quantize_convolutions
(graph: Graph) → None¶ - Given a convolution node C, if C has proper quantization details, it will mark C as quantized and it will
assign the correct output data types to the node C and its quantizers. Note that the expected output data type on the runtime is defined as QUANTIZED_NOT_PACKED.
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_propagate_datatypes
(graph) → None¶ Further propagate output data types.
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_propagate_format
(graph) → None¶ Further propagate output data types.
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_insert_cast
(graph: Graph) → None¶ Insert Cast Operator if needed
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_lookup
(graph: Graph, config: Config) → None¶ Lookup.
- Parameters
graph (Graph) – The input graph. It will be modified in-place.
-
blueoil.converter.core.optimizer.
pass_simplify_batchnorm
(graph: Graph) → None¶ Simplify BarchNorm operator.