InferShape

Applicability

Product	Supported
Atlas 350 Accelerator Card	√
Atlas A3 training product/Atlas A3 inference product	√
Atlas A2 training product/Atlas A2 inference product	√
Atlas 200I/500 A2 inference product	√
Atlas inference product	√
Atlas training product	√

Header File/Library File

Header file: #include <ge/ge_utils.h>
Library file: libge_compiler.so

Function Usage

Performs shape inference on the input graph based on the input shape.

This API is used only for shape inference. It does not perform any other optimizations (such as constant folding and dead-edge elimination) on the graph.

Prototype

static Status InferShape(const Graph &graph, const std::vector<Shape> &input_shape)

Parameters

Parameter	Input/Output	Description
graph	Input	Graph to be inferred.
input_shape	Input	Graph input shape.

Returns

Parameter	Type	Description
-	graphStatus	SUCCESS: Inference succeeded. FAILED: Inference failed.

Parameter

Type

Description

graphStatus

SUCCESS: Inference succeeded.

FAILED: Inference failed.

Restrictions

None

Parent topic: GeUtils