Spaces:
Running
on
L4
Running
on
L4
File size: 3,441 Bytes
5ac1897 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
# Copyright (c) OpenMMLab. All rights reserved.
import numpy as np
def _calc_distances(preds, targets, mask, normalize):
"""Calculate the normalized distances between preds and target.
Note:
batch_size: N
num_keypoints: K
dimension of keypoints: D (normally, D=2 or D=3)
Args:
preds (np.ndarray[N, K, D]): Predicted keypoint location.
targets (np.ndarray[N, K, D]): Groundtruth keypoint location.
mask (np.ndarray[N, K]): Visibility of the target. False for invisible
joints, and True for visible. Invisible joints will be ignored for
accuracy calculation.
normalize (np.ndarray[N, D]): Typical value is heatmap_size
Returns:
np.ndarray[K, N]: The normalized distances. \
If target keypoints are missing, the distance is -1.
"""
N, K, _ = preds.shape
# set mask=0 when normalize==0
_mask = mask.copy()
_mask[np.where((normalize == 0).sum(1))[0], :] = False
distances = np.full((N, K), -1, dtype=np.float32)
# handle invalid values
normalize[np.where(normalize <= 0)] = 1e6
distances[_mask] = np.linalg.norm(
((preds - targets) / normalize[:, None, :])[_mask], axis=-1)
return distances.T
def _distance_acc(distances, thr=0.5):
"""Return the percentage below the distance threshold, while ignoring
distances values with -1.
Note:
batch_size: N
Args:
distances (np.ndarray[N, ]): The normalized distances.
thr (float): Threshold of the distances.
Returns:
float: Percentage of distances below the threshold. \
If all target keypoints are missing, return -1.
"""
distance_valid = distances != -1
num_distance_valid = distance_valid.sum()
if num_distance_valid > 0:
return (distances[distance_valid] < thr).sum() / num_distance_valid
return -1
def keypoint_pck_accuracy(pred, gt, mask, thr, normalize):
"""Calculate the pose accuracy of PCK for each individual keypoint and the
averaged accuracy across all keypoints for coordinates.
Note:
PCK metric measures accuracy of the localization of the body joints.
The distances between predicted positions and the ground-truth ones
are typically normalized by the bounding box size.
The threshold (thr) of the normalized distance is commonly set
as 0.05, 0.1 or 0.2 etc.
- batch_size: N
- num_keypoints: K
Args:
pred (np.ndarray[N, K, 2]): Predicted keypoint location.
gt (np.ndarray[N, K, 2]): Groundtruth keypoint location.
mask (np.ndarray[N, K]): Visibility of the target. False for invisible
joints, and True for visible. Invisible joints will be ignored for
accuracy calculation.
thr (float): Threshold of PCK calculation.
normalize (np.ndarray[N, 2]): Normalization factor for H&W.
Returns:
tuple: A tuple containing keypoint accuracy.
- acc (np.ndarray[K]): Accuracy of each keypoint.
- avg_acc (float): Averaged accuracy across all keypoints.
- cnt (int): Number of valid keypoints.
"""
distances = _calc_distances(pred, gt, mask, normalize)
acc = np.array([_distance_acc(d, thr) for d in distances])
valid_acc = acc[acc >= 0]
cnt = len(valid_acc)
avg_acc = valid_acc.mean() if cnt > 0 else 0
return acc, avg_acc, cnt
|