GradientError¶

class mmeval.metrics.GradientError(sigma: float = 1.4, norm_const: int = 1000, **kwargs)[source]¶

Gradient error for evaluating alpha matte prediction.

Parameters

sigma (float) – Standard deviation of the gaussian kernel. Defaults to 1.4 .
norm_const (int) – Divide the result to reduce its magnitude. Defaults to 1000.
**kwargs – Keyword parameters passed to BaseMetric.

Note

The current implementation assumes the image / alpha / trimap a numpy array with pixel values ranging from 0 to 255.

The pred_alpha should be masked by trimap before passing into this metric.

The trimap is the most commonly used prior knowledge. As the name implies, trimap is a ternary graph and each pixel takes one of {0, 128, 255}, representing the foreground, the unknown and the background respectively.

Examples

>>> from mmeval import GradientError
>>> import numpy as np
>>>
>>> gradient_error = GradientError()
>>> np.random.seed(0)
>>> pred_alpha = np.random.randn(32, 32).astype('uint8')
>>> gt_alpha = np.ones((32, 32), dtype=np.uint8) * 255
>>> trimap = np.zeros((32, 32), dtype=np.uint8)
>>> trimap[:16, :16] = 128
>>> trimap[16:, 16:] = 255
>>> gradient_error(pred_alpha, gt_alpha, trimap)  
{'gradient_error': ...}

add(pred_alphas: Sequence[numpy.ndarray], gt_alphas: Sequence[numpy.ndarray], trimaps: Sequence[numpy.ndarray]) → None[source]¶

Add GradientError score of batch to self._results

Parameters

pred_alphas (Sequence[np.ndarray]) – Predict the probability that pixels belong to the foreground.
gt_alphas (Sequence[np.ndarray]) – Probability that the actual pixel belongs to the foreground.
trimaps (Sequence[np.ndarray]) – Broadly speaking, the trimap consists of foreground and unknown region.

compute_metric(results: List) → Dict[str, float][source]¶

Compute the GradientError metric.

Parameters: results (List) – A list that consisting the GradientError score. This list has already been synced across all ranks.
Returns: The computed GradientError metric. The keys are the names of the metrics, and the values are corresponding results.
Return type: Dict[str, float]