Source code
Revision control
Copy as Markdown
Other Tools
Test Info:
- This WPT test may be referenced by the following Test IDs:
- /webnn/conformance_tests/log.https.any.html?cpu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/log.https.any.html?gpu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/log.https.any.html?npu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/log.https.any.worker.html?cpu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/log.https.any.worker.html?gpu - WPT Dashboard Interop Dashboard
- /webnn/conformance_tests/log.https.any.worker.html?npu - WPT Dashboard Interop Dashboard
// META: title=test WebNN API element-wise log operation
// META: global=window,dedicatedworker
// META: variant=?cpu
// META: variant=?gpu
// META: variant=?npu
// META: script=../resources/utils.js
// META: timeout=long
'use strict';
// Compute the natural logarithm of the input tensor, element-wise.
//
// MLOperand log(MLOperand input);
const getLogPrecisionTolerance = (graphResources) => {
const toleranceValueDict = {float32: 1 / 1024, float16: 1 / 1024};
const expectedDataType =
getExpectedDataTypeOfSingleOutput(graphResources.expectedOutputs);
return {metricType: 'ATOL', value: toleranceValueDict[expectedDataType]};
};
const logTests = [
{
'name': 'log float32 positive 0D scalar',
'graph': {
'inputs': {
'logInput': {
'data': [63.82542037963867],
'descriptor': {shape: [], dataType: 'float32'}
}
},
'operators': [{
'name': 'log',
'arguments': [{'input': 'logInput'}],
'outputs': 'logOutput'
}],
'expectedOutputs': {
'logOutput': {
'data': [4.15615177154541],
'descriptor': {shape: [], dataType: 'float32'}
}
}
}
},
{
'name': 'log float32 positive 1D constant tensor',
'graph': {
'inputs': {
'logInput': {
'data': [
63.82542037963867, 25.317724227905273, 96.44790649414062,
40.91856384277344, 36.579071044921875, 57.81629943847656,
10.057244300842285, 17.836828231811523, 50.79246520996094,
83.860595703125, 12.065509796142578, 22.702478408813477,
47.559814453125, 17.543880462646484, 32.65243911743164,
20.353010177612305, 52.54472351074219, 45.608802795410156,
30.385812759399414, 13.709558486938477, 10.396759986877441,
50.840946197509766, 5.682034492492676, 94.02275848388672
],
'descriptor': {shape: [24], dataType: 'float32'},
'constant': true
}
},
'operators': [{
'name': 'log',
'arguments': [{'input': 'logInput'}],
'outputs': 'logOutput'
}],
'expectedOutputs': {
'logOutput': {
'data': [
4.15615177154541, 3.2315046787261963, 4.569003105163574,
3.7115838527679443, 3.5994763374328613, 4.057270526885986,
2.308293104171753, 2.88126540184021, 3.927747964859009,
4.4291558265686035, 2.4903509616851807, 3.122474193572998,
3.861988067626953, 2.8647050857543945, 3.48591947555542,
3.0132288932800293, 3.9616646766662598, 3.820100784301758,
3.413975715637207, 2.618093252182007, 2.34149432182312,
3.9287021160125732, 1.7373093366622925, 4.54353666305542
],
'descriptor': {shape: [24], dataType: 'float32'}
}
}
}
},
{
'name': 'log float32 positive 1D tensor',
'graph': {
'inputs': {
'logInput': {
'data': [
63.82542037963867, 25.317724227905273, 96.44790649414062,
40.91856384277344, 36.579071044921875, 57.81629943847656,
10.057244300842285, 17.836828231811523, 50.79246520996094,
83.860595703125, 12.065509796142578, 22.702478408813477,
47.559814453125, 17.543880462646484, 32.65243911743164,
20.353010177612305, 52.54472351074219, 45.608802795410156,
30.385812759399414, 13.709558486938477, 10.396759986877441,
50.840946197509766, 5.682034492492676, 94.02275848388672
],
'descriptor': {shape: [24], dataType: 'float32'}
}
},
'operators': [{
'name': 'log',
'arguments': [{'input': 'logInput'}],
'outputs': 'logOutput'
}],
'expectedOutputs': {
'logOutput': {
'data': [
4.15615177154541, 3.2315046787261963, 4.569003105163574,
3.7115838527679443, 3.5994763374328613, 4.057270526885986,
2.308293104171753, 2.88126540184021, 3.927747964859009,
4.4291558265686035, 2.4903509616851807, 3.122474193572998,
3.861988067626953, 2.8647050857543945, 3.48591947555542,
3.0132288932800293, 3.9616646766662598, 3.820100784301758,
3.413975715637207, 2.618093252182007, 2.34149432182312,
3.9287021160125732, 1.7373093366622925, 4.54353666305542
],
'descriptor': {shape: [24], dataType: 'float32'}
}
}
}
},
{
'name': 'log float32 positive 2D tensor',
'graph': {
'inputs': {
'logInput': {
'data': [
63.82542037963867, 25.317724227905273, 96.44790649414062,
40.91856384277344, 36.579071044921875, 57.81629943847656,
10.057244300842285, 17.836828231811523, 50.79246520996094,
83.860595703125, 12.065509796142578, 22.702478408813477,
47.559814453125, 17.543880462646484, 32.65243911743164,
20.353010177612305, 52.54472351074219, 45.608802795410156,
30.385812759399414, 13.709558486938477, 10.396759986877441,
50.840946197509766, 5.682034492492676, 94.02275848388672
],
'descriptor': {shape: [4, 6], dataType: 'float32'}
}
},
'operators': [{
'name': 'log',
'arguments': [{'input': 'logInput'}],
'outputs': 'logOutput'
}],
'expectedOutputs': {
'logOutput': {
'data': [
4.15615177154541, 3.2315046787261963, 4.569003105163574,
3.7115838527679443, 3.5994763374328613, 4.057270526885986,
2.308293104171753, 2.88126540184021, 3.927747964859009,
4.4291558265686035, 2.4903509616851807, 3.122474193572998,
3.861988067626953, 2.8647050857543945, 3.48591947555542,
3.0132288932800293, 3.9616646766662598, 3.820100784301758,
3.413975715637207, 2.618093252182007, 2.34149432182312,
3.9287021160125732, 1.7373093366622925, 4.54353666305542
],
'descriptor': {shape: [4, 6], dataType: 'float32'}
}
}
}
},
{
'name': 'log float32 positive 3D tensor',
'graph': {
'inputs': {
'logInput': {
'data': [
63.82542037963867, 25.317724227905273, 96.44790649414062,
40.91856384277344, 36.579071044921875, 57.81629943847656,
10.057244300842285, 17.836828231811523, 50.79246520996094,
83.860595703125, 12.065509796142578, 22.702478408813477,
47.559814453125, 17.543880462646484, 32.65243911743164,
20.353010177612305, 52.54472351074219, 45.608802795410156,
30.385812759399414, 13.709558486938477, 10.396759986877441,
50.840946197509766, 5.682034492492676, 94.02275848388672
],
'descriptor': {shape: [2, 3, 4], dataType: 'float32'}
}
},
'operators': [{
'name': 'log',
'arguments': [{'input': 'logInput'}],
'outputs': 'logOutput'
}],
'expectedOutputs': {
'logOutput': {
'data': [
4.15615177154541, 3.2315046787261963, 4.569003105163574,
3.7115838527679443, 3.5994763374328613, 4.057270526885986,
2.308293104171753, 2.88126540184021, 3.927747964859009,
4.4291558265686035, 2.4903509616851807, 3.122474193572998,
3.861988067626953, 2.8647050857543945, 3.48591947555542,
3.0132288932800293, 3.9616646766662598, 3.820100784301758,
3.413975715637207, 2.618093252182007, 2.34149432182312,
3.9287021160125732, 1.7373093366622925, 4.54353666305542
],
'descriptor': {shape: [2, 3, 4], dataType: 'float32'}
}
}
}
},
{
'name': 'log float32 positive 4D tensor',
'graph': {
'inputs': {
'logInput': {
'data': [
63.82542037963867, 25.317724227905273, 96.44790649414062,
40.91856384277344, 36.579071044921875, 57.81629943847656,
10.057244300842285, 17.836828231811523, 50.79246520996094,
83.860595703125, 12.065509796142578, 22.702478408813477,
47.559814453125, 17.543880462646484, 32.65243911743164,
20.353010177612305, 52.54472351074219, 45.608802795410156,
30.385812759399414, 13.709558486938477, 10.396759986877441,
50.840946197509766, 5.682034492492676, 94.02275848388672
],
'descriptor': {shape: [2, 2, 2, 3], dataType: 'float32'}
}
},
'operators': [{
'name': 'log',
'arguments': [{'input': 'logInput'}],
'outputs': 'logOutput'
}],
'expectedOutputs': {
'logOutput': {
'data': [
4.15615177154541, 3.2315046787261963, 4.569003105163574,
3.7115838527679443, 3.5994763374328613, 4.057270526885986,
2.308293104171753, 2.88126540184021, 3.927747964859009,
4.4291558265686035, 2.4903509616851807, 3.122474193572998,
3.861988067626953, 2.8647050857543945, 3.48591947555542,
3.0132288932800293, 3.9616646766662598, 3.820100784301758,
3.413975715637207, 2.618093252182007, 2.34149432182312,
3.9287021160125732, 1.7373093366622925, 4.54353666305542
],
'descriptor': {shape: [2, 2, 2, 3], dataType: 'float32'}
}
}
}
},
{
'name': 'log float32 positive 5D tensor',
'graph': {
'inputs': {
'logInput': {
'data': [
63.82542037963867, 25.317724227905273, 96.44790649414062,
40.91856384277344, 36.579071044921875, 57.81629943847656,
10.057244300842285, 17.836828231811523, 50.79246520996094,
83.860595703125, 12.065509796142578, 22.702478408813477,
47.559814453125, 17.543880462646484, 32.65243911743164,
20.353010177612305, 52.54472351074219, 45.608802795410156,
30.385812759399414, 13.709558486938477, 10.396759986877441,
50.840946197509766, 5.682034492492676, 94.02275848388672
],
'descriptor': {shape: [2, 1, 4, 1, 3], dataType: 'float32'}
}
},
'operators': [{
'name': 'log',
'arguments': [{'input': 'logInput'}],
'outputs': 'logOutput'
}],
'expectedOutputs': {
'logOutput': {
'data': [
4.15615177154541, 3.2315046787261963, 4.569003105163574,
3.7115838527679443, 3.5994763374328613, 4.057270526885986,
2.308293104171753, 2.88126540184021, 3.927747964859009,
4.4291558265686035, 2.4903509616851807, 3.122474193572998,
3.861988067626953, 2.8647050857543945, 3.48591947555542,
3.0132288932800293, 3.9616646766662598, 3.820100784301758,
3.413975715637207, 2.618093252182007, 2.34149432182312,
3.9287021160125732, 1.7373093366622925, 4.54353666305542
],
'descriptor': {shape: [2, 1, 4, 1, 3], dataType: 'float32'}
}
}
}
}
];
if (navigator.ml) {
logTests.forEach((test) => {
webnn_conformance_test(
buildAndExecuteGraph, getLogPrecisionTolerance, test);
});
} else {
test(() => assert_implements(navigator.ml, 'missing navigator.ml'));
}