yobx.xoptim.patterns.onnx_slice

class yobx.xoptim.patterns.onnx_slice.SliceSlicePattern(verbose: int = 0, priority: int = 1, min_opset: int = 1)

Merges consecutive slices if axis are disjoints.

Model with nodes to be fused:

        graph TD

    classDef ioNode fill:#dfd,stroke:#333,color:#333
    classDef initNode fill:#cccc00,stroke:#333,color:#333
    classDef constNode fill:#f9f,stroke:#333,stroke-width:2px,color:#333
    classDef opNode fill:#bbf,stroke:#333,stroke-width:2px,color:#333

    I_X(["X FLOAT(a, b)"])
    I_one(["one INT64(1)"])
    I_zero(["zero INT64(1)"])

    Constant_0[["Constant() -#gt; zero"]]
    Constant_1[["Constant() -#gt; one"]]
    Slice_2[["Slice(., ., ., .)"]]
    Slice_3[["Slice(., ., ., .)"]]

    I_X -->|"FLOAT(a, b)"| Slice_2
    Constant_0 -->|"INT64(1)"| Slice_2
    Constant_1 -->|"INT64(1)"| Slice_2
    Slice_2 -->|"FLOAT(1, b)"| Slice_3
    Constant_0 -->|"INT64(1)"| Slice_3
    Constant_1 -->|"INT64(1)"| Slice_3

    O_Y(["Y FLOAT(c, d)"])
    Slice_3 --> O_Y

    class I_X,I_one,I_zero,O_Y ioNode
    class Constant_0,Constant_1 constNode
    class Slice_2,Slice_3 opNode
    

Outcome of the fusion:

        graph TD

    classDef ioNode fill:#dfd,stroke:#333,color:#333
    classDef initNode fill:#cccc00,stroke:#333,color:#333
    classDef constNode fill:#f9f,stroke:#333,stroke-width:2px,color:#333
    classDef opNode fill:#bbf,stroke:#333,stroke-width:2px,color:#333

    I_X(["X FLOAT(a, b)"])
    I_one(["one INT64(1)"])
    I_zero(["zero INT64(1)"])

    Concat_0[["Concat(., ., axis=0)"]]
    Concat_1[["Concat(., ., axis=0)"]]
    Concat_2[["Concat(., ., axis=0)"]]
    Slice_3[["Slice(., ., ., .)"]]

    I_zero -->|"INT64(1)"| Concat_0
    I_one -->|"INT64(1)"| Concat_1
    I_zero -->|"INT64(1)"| Concat_2
    I_one -->|"INT64(1)"| Concat_2
    I_X -->|"FLOAT(a, b)"| Slice_3
    Concat_0 -->|"INT64(2)"| Slice_3
    Concat_1 -->|"INT64(2)"| Slice_3
    Concat_2 -->|"INT64(2)"| Slice_3

    O_Y(["Y FLOAT(c, d)"])
    Slice_3 --> O_Y

    class I_X,I_one,I_zero,O_Y ioNode
    class Concat_0,Concat_1,Concat_2,Slice_3 opNode
    

apply(g: GraphBuilder, before: NodeProto, node: NodeProto) → List[NodeProto]

The method does the rewriting. It assumes it can happen. It takes a list of nodes impacted by the rewriting assumes no other pattern optimizer will be modify them. It receives the list of nodes returned by method apply. Since it is a list of argument, method match can include None values. The method returns the new nodes. The optimizer considers that any node given to this function is removed from the graph, and any node returned by it are added. If a received node must be kept, it must be added to the list of returned node.

Parameters:

nodes – nodes returned by method match, there are then removed

Returns:

nodes to add to graph.

match(g: GraphBuilderPatternOptimization, node: NodeProto, matched: List[MatchResult]) → MatchResult | None

Determines nodes around node which can be rewritten.

Parameters:

• g – is a GraphBuilderPatternOptimization, it holds all the existing nodes, is able to return any information about type, shape, the node before, the node after another one.

• node – the matching must determine if some nodes around this one are part of set of nodes this pattern optimizer can rewrite. From there, the function explores wherever it needs, checking any condition it needs.

• matched – usually unused, it returns of nodes already matching a pattern

The method must not modify the graph. The method returns None if no match is found or an instance of class MatchResult. It must contain:

• a list of nodes involved in the rewriting. It does not mean all of them will be removed but all of them are needed to do the rewriting and must not be impacted by other pattern optimizer.

• A function doing the rewriting (usually method apply of the pattern class).

• An existing node where the rewritten nodes can be inserted. Knowing it makes it faster to rewriter. If not specified, the optimizer will automatically determine the position of the new nodes.