MeanSquaredError¶
- class mmeval.metrics.MeanSquaredError(**kwargs)[source]¶
Mean Squared Error metric for image.
Formula: mean((a-b)^2).
- Parameters
**kwargs – Keyword parameters passed to
BaseMetric
.
Examples
>>> from mmeval import MeanSquaredError as MSE >>> import numpy as np >>> >>> mse = MSE() >>> gts = np.random.randint(0, 255, size=(3, 32, 32)) >>> preds = np.random.randint(0, 255, size=(3, 32, 32)) >>> mse(preds, gts) {'mse': ...}
Calculate MeanSquaredError between 2 images with mask:
>>> img1 = np.ones((32, 32, 3)) >>> img2 = np.ones((32, 32, 3)) * 2 >>> mask = np.ones((32, 32, 3)) * 2 >>> mask[:16] *= 0 >>> MSE.compute_mse(img1, img2, mask) 0.000015378700496
- add(predictions: Sequence[numpy.ndarray], groundtruths: Sequence[numpy.ndarray], masks: Optional[Sequence[numpy.ndarray]] = None) → None[source]¶
Add MeanSquaredError score of batch to
self._results
- Parameters
predictions (Sequence[np.ndarray]) – Predictions of the model.
groundtruths (Sequence[np.ndarray]) – The ground truth images.
masks (Sequence[np.ndarray], optional) – Mask images.
- compute_metric(results: List[numpy.float32]) → Dict[str, float][source]¶
Compute the MeanSquaredError metric.
This method would be invoked in
BaseMetric.compute
after distributed synchronization.- Parameters
results (List[np.float32]) – A list that consisting the MeanSquaredError score. This list has already been synced across all ranks.
- Returns
The computed MeanSquaredError metric.
- Return type
Dict[str, float]
- static compute_mse(prediction: numpy.ndarray, groundtruth: numpy.ndarray, mask: Optional[numpy.ndarray] = None) → numpy.float32[source]¶
Calculate MeanSquaredError (Mean Squared Error).
- Parameters
prediction (np.ndarray) – Images with range [0, 255].
groundtruth (np.ndarray) – Images with range [0, 255].
mask (np.ndarray, optional) – Mask of evaluation.
- Returns
MeanSquaredError result.
- Return type
np.float32