chromium/third_party/blink/web_tests/platform/mac/virtual/webnn-service-with-gpu/external/wpt/webnn/conformance_tests/conv2d.https.any.worker_gpu-expected.txt

This is a testharness.js-based test.
[FAIL] conv2d float32 4D both input and filter non-constant tensors default options
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 1.53125 should be close enough to expected 1.5323282480239868 by the acceptable 18 ULP distance, but they have 9045 ULP distance expected true got false
[FAIL] conv2d float32 4D both input and filter constant tensors default options
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 1.53125 should be close enough to expected 1.5323282480239868 by the acceptable 18 ULP distance, but they have 9045 ULP distance expected true got false
[FAIL] conv2d float32 4D input and filter tensors default options
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 1.53125 should be close enough to expected 1.5323282480239868 by the acceptable 18 ULP distance, but they have 9045 ULP distance expected true got false
[FAIL] conv2d float32 4D input and filter tensors options.padding
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 1.0380859375 should be close enough to expected 1.0390141010284424 by the acceptable 18 ULP distance, but they have 7786 ULP distance expected true got false
[FAIL] conv2d float32 4D input and filter tensors options.strides
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 1.53125 should be close enough to expected 1.5323282480239868 by the acceptable 18 ULP distance, but they have 9045 ULP distance expected true got false
[FAIL] conv2d float32 4D input and filter tensors options.dilations
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 1.359375 should be close enough to expected 1.3599307537078857 by the acceptable 18 ULP distance, but they have 4662 ULP distance expected true got false
[FAIL] depthwise conv2d float32 4D input and filter tensors options.groups= input_channels
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 1.1796875 should be close enough to expected 1.1808103322982788 by the acceptable 8 ULP distance, but they have 9419 ULP distance expected true got false
[FAIL] conv2d float32 4D input and filter tensors options.inputLayout='nchw'
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 0.88427734375 should be close enough to expected 0.8845428228378296 by the acceptable 8 ULP distance, but they have 4454 ULP distance expected true got false
[FAIL] conv2d float32 4D input and filter tensors options.filterLayout='oihw'
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 0.88427734375 should be close enough to expected 0.8845428228378296 by the acceptable 8 ULP distance, but they have 4454 ULP distance expected true got false
[FAIL] conv2d float32 4D input and filter tensors 1D options.bias
  assert_true: assert_array_approx_equals_ulp: test conv2d float32 actual 1.697265625 should be close enough to expected 1.698119044303894 by the acceptable 8 ULP distance, but they have 7159 ULP distance expected true got false
Harness: the test ran to completion.