KeypointNME

class mmeval.metrics.KeypointNME(norm_mode: str, norm_item: Optional[str] = None, keypoint_indices: Optional[Sequence[int]] = None, **kwargs)

NME evaluation metric.

Calculate the normalized mean error (NME) of keypoints.

Note

• length of dataset: N

• num_keypoints: K

• number of keypoint dimensions: D (typically D = 2)

Parameters

• norm_mode (str) –

  The normalization mode, which should be one of the following options:

  • 'use_norm_item': Should specify the argument norm_item, which represents the item in the datainfo that will be used as the normalization factor.

  • 'keypoint_distance': Should specify the argument keypoint_indices that are used to calculate the keypoint distance as the normalization factor.

• norm_item (str, optional) – The item used as the normalization factor. For example, ‘box_size’ in ‘AFLWDataset’. Only valid when norm_mode is use_norm_item. Defaults to None.

• keypoint_indices (Sequence[int], optional) – The keypoint indices used to calculate the keypoint distance as the normalization factor. Only valid when norm_mode is keypoint_distance. If set as None, will use the default keypoint_indices in DEFAULT_KEYPOINT_INDICES for specific datasets, else use the given keypoint_indices of the dataset. Defaults to None.

• **kwargs – Keyword parameters passed to BaseMetric.

Examples

>>> from mmeval.metrics import KeypointNME
>>> import numpy as np
>>> aflw_dataset_meta = {
...     'dataset_name': 'aflw',
...     'num_keypoints': 19,
...     'sigmas': np.array([]),
... }
>>> nme_metric = KeypointNME(
...     norm_mode='use_norm_item',
...     norm_item=norm_item,
...     dataset_meta=aflw_dataset_meta)
>>> batch_size = 2
>>> predictions = [{
...     'coords': np.zeros((1, 19, 2))
... } for _ in range(batch_size)]
>>> groundtruths = [{
...     'coords': np.zeros((1, 19, 2)) + 0.5,
...     'mask': np.ones((1, 19)).astype(bool),
...     'box_size': np.ones((1, 1)) * i * 20
... } for i in range(batch_size)]
>>> norm_item = 'box_size'
>>> nme_metric(predictions, groundtruths)
OrderedDict([('NME', 0.03535533892480951)])

add(predictions: Sequence[Dict], groundtruths: Sequence[Dict]) → None

Add the intermediate results to self._results.

Parameters

• predictions (Sequence[dict]) –

  A sequence of dict. Each prediction dict has the following keys:

  • coords (np.ndarray, [1, K, D]): predicted keypoints coordinates

• groundtruths (Sequence[dict]) –

  The ground truth labels. Each groundtruth dict has the following keys:

  • coords (np.ndarray, [1, K, D]): ground truth keypoints coordinates

  • mask (np.ndarray, [1, K]): ground truth keypoints_visible

  There are some optional keys as well:

  • bboxes: it is necessary when self.norm_item is ‘bbox_size’

  • self.norm_item: it is necessary when self.norm_item is neither None nor ‘bbox_size’

compute_metric(results: list) → Dict[str, float]

Compute the metrics from processed results.

Parameters

results (list) – The processed results of each batch.

Returns

The computed metrics. The keys are the names of the metrics, and the values are the corresponding results.

Return type

Dict[str, float]