ai.onnx.Shrink

ai.onnx · standard ONNX operator · ONNX opset ≥ 9

Description

Applies an elementwise shrinkage function to a numeric tensor: values outside [-lambd, lambd] are shifted toward zero by bias, and values within the range are set to 0. Formally: y = x + bias if x < -lambd; y = x - bias if x > lambd; otherwise y = 0. Output has the same shape and dtype as the input.

See the ONNX Shrink spec for the reference semantics.

Inputs

Outputs

Attributes

Default values (overridable per request):

Type constraints

Files

• metadata.json — kernel metadata (id, digests, provenance)
• manifest.json — the op contract (source of truth)
• test.json — correctness cases
• bench.json — benchmark + tuning cases
• unary-scalar.wgsl.jinja
• unary-vec4.wgsl.jinja

Use with @huggingface/kernels

The loader derives every required output's shape and logical dtype from the manifest contract and this call. It then allocates the result tensors automatically.

The version: 1 option selects the published kernel contract; it is independent of any operator opset, contrib since_version, or model version.

Replace each *Data placeholder with a typed array containing the corresponding input data.

import { getKernel } from "@huggingface/kernels";

const kernel = await getKernel("webgpu-kernels/ai.onnx.Shrink", { version: 1 });
const { y } = await kernel({ x: { data: xData, shape: [2, 2] } });