PeakSignalNoiseRatio

class mmeval.metrics.PeakSignalNoiseRatio(crop_border: int = 0, input_order: str = 'CHW', convert_to: Optional[str] = None, channel_order: str = 'rgb', **kwargs)

Peak Signal-to-Noise Ratio.

Ref: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio

参数

• crop_border (int) – Cropped pixels in each edges of an image. These pixels are not involved in the PeakSignalNoiseRatio calculation. Defaults to 0.

• input_order (str) – Whether the input order is ‘HWC’ or ‘CHW’. Defaults to ‘CHW’.

• convert_to (str) – Whether to convert the images to other color models. If None, the images are not altered. When computing for ‘Y’, the images are assumed to be in BGR order. Options are ‘Y’ and None. Defaults to None.

• channel_order (str) – The channel order of image. Defaults to ‘rgb’.

• **kwargs – Keyword parameters passed to BaseMetric.

实际案例

>>> from mmeval import PeakSignalNoiseRatio as PSNR
>>> import numpy as np
>>>
>>> psnr = PSNR(input_order='CHW', convert_to='Y', channel_order='rgb')
>>> gts = np.random.randint(0, 255, size=(3, 32, 32))
>>> preds = np.random.randint(0, 255, size=(3, 32, 32))
>>> psnr(preds, gts)  
{'psnr': ...}

Calculate PeakSignalNoiseRatio between 2 single channel images:

>>> img1 = np.ones((32, 32))
>>> img2 = np.ones((32, 32))
>>> PSNR.compute_psnr(img1, img2)
49.45272242415597

add(predictions: Sequence[numpy.ndarray], groundtruths: Sequence[numpy.ndarray], channel_order: Optional[str] = None) → None

Add PeakSignalNoiseRatio score of batch to self._results

参数

• predictions (Sequence[np.ndarray]) – Predictions of the model.

• groundtruths (Sequence[np.ndarray]) – The ground truth images.

• channel_order (Optional[str]) – The channel order of the input samples. If not passed, will set as self.channel_order. Defaults to None.

compute_metric(results: List[numpy.float64]) → Dict[str, float]

Compute the PeakSignalNoiseRatio metric.

This method would be invoked in BaseMetric.compute after distributed synchronization.

参数

results (List[np.float64]) – A list that consisting the PeakSignalNoiseRatio score. This list has already been synced across all ranks.

返回

The computed PeakSignalNoiseRatio metric.

返回类型

Dict[str, float]

static compute_psnr(prediction: numpy.ndarray, groundtruth: numpy.ndarray) → numpy.float64

Calculate PeakSignalNoiseRatio (Peak Signal-to-Noise Ratio).

Ref: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio

参数

• prediction (np.ndarray) – Images with range [0, 255].

• groundtruth (np.ndarray) – Images with range [0, 255].

返回

PeakSignalNoiseRatio result.

返回类型

np.float64