Source code
Revision control
Copy as Markdown
Other Tools
Test Info: Warnings
- This test has a WPT meta file that expects 1 subtest issues.
- This WPT test may be referenced by the following Test IDs:
- /webnn/conformance_tests/hard_sigmoid.https.any.html?cpu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/hard_sigmoid.https.any.html?gpu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/hard_sigmoid.https.any.html?npu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/hard_sigmoid.https.any.worker.html?cpu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/hard_sigmoid.https.any.worker.html?gpu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/hard_sigmoid.https.any.worker.html?npu - WPT Dashboard Interop Dashboard
// META: title=test WebNN API hardSigmoid operation
// META: global=window,dedicatedworker
// META: variant=?cpu
// META: variant=?gpu
// META: variant=?npu
// META: script=../resources/utils.js
// META: timeout=long
'use strict';
// Calculate the non-smooth hard sigmoid function on the input tensor, used
// instead of the sigmoid function for faster computation.
//
// dictionary MLHardSigmoidOptions {
// double alpha = 0.2;
// double beta = 0.5;
// };
//
// MLOperand hardSigmoid(
// MLOperand input, optional MLHardSigmoidOptions options = {});
const hardSigmoidTests = [
{
'name': 'hardSigmoid float32 positive 0D tensor default options',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [0.05907066911458969],
'descriptor': {shape: [], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [{'input': 'hardSigmoidInput'}],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [0.5118141174316406],
'descriptor': {shape: [], dataType: 'float32'}
}
}
}
},
{
'name': 'hardSigmoid float32 positive 1D constant tensor default options',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [24], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [{'input': 'hardSigmoidInput'}],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.5118141174316406, 0.6415218114852905, 0.6045681238174438,
0.5846202969551086, 0.6328738331794739, 0.6900588274002075,
0.5218378305435181, 0.5025954246520996, 0.5951059460639954,
0.6064510345458984, 0.6368615627288818, 0.5932421684265137,
0.5609799027442932, 0.6605174541473389, 0.5497192740440369,
0.6327379941940308, 0.6109522581100464, 0.6108517050743103,
0.6462276577949524, 0.5976191759109497, 0.6553369164466858,
0.669111430644989, 0.6110604405403137, 0.6120688915252686
],
'descriptor': {shape: [24], dataType: 'float32'}
}
}
}
},
{
'name': 'hardSigmoid float32 positive 1D tensor default options',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [24], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [{'input': 'hardSigmoidInput'}],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.5118141174316406, 0.6415218114852905, 0.6045681238174438,
0.5846202969551086, 0.6328738331794739, 0.6900588274002075,
0.5218378305435181, 0.5025954246520996, 0.5951059460639954,
0.6064510345458984, 0.6368615627288818, 0.5932421684265137,
0.5609799027442932, 0.6605174541473389, 0.5497192740440369,
0.6327379941940308, 0.6109522581100464, 0.6108517050743103,
0.6462276577949524, 0.5976191759109497, 0.6553369164466858,
0.669111430644989, 0.6110604405403137, 0.6120688915252686
],
'descriptor': {shape: [24], dataType: 'float32'}
}
}
}
},
{
'name': 'hardSigmoid float32 positive 2D tensor default options',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [4, 6], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [{'input': 'hardSigmoidInput'}],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.5118141174316406, 0.6415218114852905, 0.6045681238174438,
0.5846202969551086, 0.6328738331794739, 0.6900588274002075,
0.5218378305435181, 0.5025954246520996, 0.5951059460639954,
0.6064510345458984, 0.6368615627288818, 0.5932421684265137,
0.5609799027442932, 0.6605174541473389, 0.5497192740440369,
0.6327379941940308, 0.6109522581100464, 0.6108517050743103,
0.6462276577949524, 0.5976191759109497, 0.6553369164466858,
0.669111430644989, 0.6110604405403137, 0.6120688915252686
],
'descriptor': {shape: [4, 6], dataType: 'float32'}
}
}
}
},
{
'name': 'hardSigmoid float32 positive 3D tensor default options',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [{'input': 'hardSigmoidInput'}],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.5118141174316406, 0.6415218114852905, 0.6045681238174438,
0.5846202969551086, 0.6328738331794739, 0.6900588274002075,
0.5218378305435181, 0.5025954246520996, 0.5951059460639954,
0.6064510345458984, 0.6368615627288818, 0.5932421684265137,
0.5609799027442932, 0.6605174541473389, 0.5497192740440369,
0.6327379941940308, 0.6109522581100464, 0.6108517050743103,
0.6462276577949524, 0.5976191759109497, 0.6553369164466858,
0.669111430644989, 0.6110604405403137, 0.6120688915252686
],
'descriptor': {shape: [2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name': 'hardSigmoid float32 positive 4D tensor default options',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [{'input': 'hardSigmoidInput'}],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.5118141174316406, 0.6415218114852905, 0.6045681238174438,
0.5846202969551086, 0.6328738331794739, 0.6900588274002075,
0.5218378305435181, 0.5025954246520996, 0.5951059460639954,
0.6064510345458984, 0.6368615627288818, 0.5932421684265137,
0.5609799027442932, 0.6605174541473389, 0.5497192740440369,
0.6327379941940308, 0.6109522581100464, 0.6108517050743103,
0.6462276577949524, 0.5976191759109497, 0.6553369164466858,
0.669111430644989, 0.6110604405403137, 0.6120688915252686
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name': 'hardSigmoid float32 positive 5D tensor default options',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [1, 2, 1, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [{'input': 'hardSigmoidInput'}],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.5118141174316406, 0.6415218114852905, 0.6045681238174438,
0.5846202969551086, 0.6328738331794739, 0.6900588274002075,
0.5218378305435181, 0.5025954246520996, 0.5951059460639954,
0.6064510345458984, 0.6368615627288818, 0.5932421684265137,
0.5609799027442932, 0.6605174541473389, 0.5497192740440369,
0.6327379941940308, 0.6109522581100464, 0.6108517050743103,
0.6462276577949524, 0.5976191759109497, 0.6553369164466858,
0.669111430644989, 0.6110604405403137, 0.6120688915252686
],
'descriptor': {shape: [1, 2, 1, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name':
'hardSigmoid float32 positive 4D tensor specified positive options.alpha default options.beta',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [
{'input': 'hardSigmoidInput'},
{'options': {'alpha': 0.7854232544278235}}
],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.546395480632782,
1,
0.9106510877609253,
0.8323138356208801,
1,
1,
0.5857596397399902,
0.5101925134658813,
0.8734921216964722,
0.9180455803871155,
1,
0.8661727905273438,
0.7394752502441406,
1,
0.6952533721923828,
1,
0.9357223510742188,
0.9353274703025818,
1,
0.8833619952201843,
1,
1,
0.936147153377533,
0.9401075839996338
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name':
'hardSigmoid float32 negative 4D tensor specified negative options.alpha default options.beta',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
-0.05907066911458969, -0.7076089382171631, -0.5228404998779297,
-0.4231015741825104, -0.6643692851066589, -0.950294017791748,
-0.10918906331062317, -0.0129771139472723, -0.4755297303199768,
-0.5322551727294922, -0.684307873249054, -0.4662107527256012,
-0.3048996329307556, -0.8025872707366943, -0.2485964000225067,
-0.663689911365509, -0.5547611713409424, -0.554258406162262,
-0.7311381697654724, -0.4880960285663605, -0.7766845226287842,
-0.8455570340156555, -0.555302083492279, -0.5603444576263428
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [
{'input': 'hardSigmoidInput'},
{'options': {'alpha': -0.7854232544278235}}
],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.546395480632782,
1,
0.9106510877609253,
0.8323138356208801,
1,
1,
0.5857596397399902,
0.5101925134658813,
0.8734921216964722,
0.9180455803871155,
1,
0.8661727905273438,
0.7394752502441406,
1,
0.6952533721923828,
1,
0.9357223510742188,
0.9353274703025818,
1,
0.8833619952201843,
1,
1,
0.936147153377533,
0.9401075839996338
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name':
'hardSigmoid float32 positive 4D tensor specified positive options.beta default options.alpha',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [
{'input': 'hardSigmoidInput'},
{'options': {'beta': 0.4361860418530341}}
],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.4480001926422119, 0.577707827091217, 0.5407541394233704,
0.5208063721656799, 0.5690599083900452, 0.626244843006134,
0.4580238461494446, 0.4387814700603485, 0.5312919616699219,
0.5426371097564697, 0.5730476379394531, 0.5294281840324402,
0.4971659779548645, 0.5967035293579102, 0.48590531945228577,
0.5689240097999573, 0.5471382737159729, 0.5470377206802368,
0.5824136734008789, 0.533805251121521, 0.5915229320526123,
0.6052974462509155, 0.5472464561462402, 0.5482549667358398
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name':
'hardSigmoid float32 negative 4D tensor specified negative options.beta default options.alpha',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
-0.05907066911458969, -0.7076089382171631, -0.5228404998779297,
-0.4231015741825104, -0.6643692851066589, -0.950294017791748,
-0.10918906331062317, -0.0129771139472723, -0.4755297303199768,
-0.5322551727294922, -0.684307873249054, -0.4662107527256012,
-0.3048996329307556, -0.8025872707366943, -0.2485964000225067,
-0.663689911365509, -0.5547611713409424, -0.554258406162262,
-0.7311381697654724, -0.4880960285663605, -0.7766845226287842,
-0.8455570340156555, -0.555302083492279, -0.5603444576263428
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [
{'input': 'hardSigmoidInput'},
{'options': {'beta': -0.436186041853034}}
],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name':
'hardSigmoid float32 positive 4D tensor specified all options (positive options.alpha and positive options.beta)',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [
{'input': 'hardSigmoidInput'},
{'options': {'alpha': 0.7854232544278235, 'beta': 0.4361860418530341}}
],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.4825815260410309,
0.9919585585594177,
0.8468371629714966,
0.7684998512268066,
0.9579971432685852,
1,
0.5219456553459167,
0.44637855887413025,
0.8096781373023987,
0.8542316555976868,
0.9736573696136475,
0.8023588061332703,
0.6756613254547119,
1,
0.6314394474029541,
0.9574635624885559,
0.8719083666801453,
0.8715134859085083,
1,
0.8195480108261108,
1,
1,
0.8723332285881042,
0.8762935996055603
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name':
'hardSigmoid float32 positive 4D tensor specified all options (negative options.alpha and negative options.beta)',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
0.05907066911458969, 0.7076089382171631, 0.5228404998779297,
0.4231015741825104, 0.6643692851066589, 0.950294017791748,
0.10918906331062317, 0.0129771139472723, 0.4755297303199768,
0.5322551727294922, 0.684307873249054, 0.4662107527256012,
0.3048996329307556, 0.8025872707366943, 0.2485964000225067,
0.663689911365509, 0.5547611713409424, 0.554258406162262,
0.7311381697654724, 0.4880960285663605, 0.7766845226287842,
0.8455570340156555, 0.555302083492279, 0.5603444576263428
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [
{'input': 'hardSigmoidInput'}, {
'options':
{'alpha': -0.7854232544278235, 'beta': -0.4361860418530341}
}
],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name':
'hardSigmoid float32 negative 4D tensor all options (positive options.alpha and negative options.beta)',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
-0.05907066911458969, -0.7076089382171631, -0.5228404998779297,
-0.4231015741825104, -0.6643692851066589, -0.950294017791748,
-0.10918906331062317, -0.0129771139472723, -0.4755297303199768,
-0.5322551727294922, -0.684307873249054, -0.4662107527256012,
-0.3048996329307556, -0.8025872707366943, -0.2485964000225067,
-0.663689911365509, -0.5547611713409424, -0.554258406162262,
-0.7311381697654724, -0.4880960285663605, -0.7766845226287842,
-0.8455570340156555, -0.555302083492279, -0.5603444576263428
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [
{'input': 'hardSigmoidInput'}, {
'options':
{'alpha': 0.7854232544278235, 'beta': -0.4361860418530341}
}
],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name':
'hardSigmoid float32 negative 4D tensor specified all options (negative options.alpha and positive options.beta)',
'graph': {
'inputs': {
'hardSigmoidInput': {
'data': [
-0.05907066911458969, -0.7076089382171631, -0.5228404998779297,
-0.4231015741825104, -0.6643692851066589, -0.950294017791748,
-0.10918906331062317, -0.0129771139472723, -0.4755297303199768,
-0.5322551727294922, -0.684307873249054, -0.4662107527256012,
-0.3048996329307556, -0.8025872707366943, -0.2485964000225067,
-0.663689911365509, -0.5547611713409424, -0.554258406162262,
-0.7311381697654724, -0.4880960285663605, -0.7766845226287842,
-0.8455570340156555, -0.555302083492279, -0.5603444576263428
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'hardSigmoid',
'arguments': [
{'input': 'hardSigmoidInput'}, {
'options':
{'alpha': -0.7854232544278235, 'beta': 0.4361860418530341}
}
],
'outputs': 'hardSigmoidOutput'
}],
'expectedOutputs': {
'hardSigmoidOutput': {
'data': [
0.4825815260410309,
0.9919585585594177,
0.8468371629714966,
0.7684998512268066,
0.9579971432685852,
1,
0.5219456553459167,
0.44637855887413025,
0.8096781373023987,
0.8542316555976868,
0.9736573696136475,
0.8023588061332703,
0.6756613254547119,
1,
0.6314394474029541,
0.9574635624885559,
0.8719083666801453,
0.8715134859085083,
1,
0.8195480108261108,
1,
1,
0.8723332285881042,
0.8762935996055603
],
'descriptor': {shape: [1, 2, 3, 4], dataType: 'float32'}
}
}
}
}
];
if (navigator.ml) {
hardSigmoidTests.forEach((test) => {
webnn_conformance_test(buildAndExecuteGraph, getPrecisionTolerance, test);
});
} else {
test(() => assert_implements(navigator.ml, 'missing navigator.ml'));
}