def compute(self):
_prediction_tensor = torch.cat(self._predictions, dim=0)
_target_tensor = torch.cat(self._targets, dim=0)
if dist.is_available() and dist.is_initialized(
) and not self._is_reduced:
_prediction_tensor = all_gather(_prediction_tensor)
_target_tensor = all_gather(_target_tensor)
self._is_reduced = True
return compute_confusion_matrix(
y_pred=_prediction_tensor,
y=_target_tensor,
to_onehot_y=self.to_onehot_y,
activation=self.activation,
bin_mode=self.bin_mode,
bin_threshold=self.bin_threshold,
metric_name=self.metric_name,
average=self.average,
zero_division=self.zero_division,
)
def test_value(self, input_data, expected_value):
result = compute_confusion_matrix(**input_data)
self.assertEqual(expected_value, result)
def test_value(self, input_data, expected_value):
result = compute_confusion_matrix(**input_data)
np.testing.assert_allclose(expected_value, result, rtol=1e-7)