WPT
wpt / webnn / validation_tests / instanceNormalization.https.any.html?gpu
Spec: Web Neural Network API ↗
Runs: Chrome 155.0.8039.0 (wpt@508cc6a62, 2026-09-03) | Firefox 157.0a1 (wpt@508cc6a62, 2026-09-03) | Safari 251 preview (wpt@5ce815a83, 2026-08-27) | Ladybird 1.0-56c61 (wpt@8fdda8ce4, 2026-09-03) | Servo Servo 0.6 (wpt@09159dcb3, 2026-09-02) | Blitz 188486089 (wpt@a95401e4e, 2026-09-02)
View on the Blitz WPT dashboard | Open test on wpt.live | wpt.fyi
| Chrome | Firefox | Safari | Ladybird | Servo | Blitz | |
|---|---|---|---|---|---|---|
| Total | 19/19 | 0/19 | 0/19 | 0/19 | 0/19 | NOT RUN |
| Subtest | Chrome | Firefox | Safari | Ladybird | Servo | Blitz |
|---|---|---|---|---|---|---|
| assert_not_equals(navigator.ml, undefined, "ml property is defined on navigator") | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] throw if input is from another builder | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] throw if scale option is from another builder | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] throw if bias option is from another builder | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Test with default options for 4-D input. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Test with scale, bias and default epsilon value. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Test with a non-default epsilon value. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Test with layout=nhwc. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Test when the input data type is float16. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the input is not a 4-D tensor. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the input data type is not one of floating point types. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the scale data type is not the same as the input data type. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the scale operand is not a 1-D tensor. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the size of scale operand is not equal to the size of the feature dimension of the input with layout=nhwc. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the size of scale operand is not equal to the size of the feature dimension of the input with layout=nchw. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the bias data type is not the same as the input data type. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the bias operand is not a 1-D tensor. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the size of bias operand is not equal to the size of the feature dimension of the input with layout=nhwc. | PASS | FAIL | FAIL | FAIL | FAIL | — |
| [instanceNormalization] Throw if the size of bias operand is not equal to the size of the feature dimension of the input with layout=nchw. | PASS | FAIL | FAIL | FAIL | FAIL | — |