def _report_metric(self, res_file, metrics, pck_thr=0.3):
"""Keypoint evaluation.
Args:
res_file (str): Json file stored prediction results.
metrics (str | list[str]): Metric to be performed.
Options: 'PCK', 'NME'.
pck_thr (float): PCK threshold, default: 0.3.
Returns:
dict: Evaluation results for evaluation metric.
"""
info_str = []
with open(res_file, 'r') as fin:
preds = json.load(fin)
assert len(preds) == len(self.db)
outputs = []
gts = []
masks = []
for pred, item in zip(preds, self.db):
outputs.append(np.array(pred['keypoints'])[:, :-1])
gts.append(np.array(item['joints_3d'])[:, :-1])
masks.append((np.array(item['joints_3d_visible'])[:, 0]) > 0)
outputs = np.array(outputs)
gts = np.array(gts)
masks = np.array(masks)
normalize_factor = self._get_normalize_factor(gts)
if 'PCK' in metrics:
_, pck, _ = keypoint_pck_accuracy(outputs, gts, masks, pck_thr,
normalize_factor)
info_str.append(('PCK', pck))
if 'NME' in metrics:
info_str.append(
('NME', keypoint_nme(outputs, gts, masks, normalize_factor)))
return info_str
def _report_metric(self, res_file, metrics):
"""Keypoint evaluation.
Args:
res_file (str): Json file stored prediction results.
metrics (str | list[str]): Metric to be performed.
Options: 'NME'.
Returns:
dict: Evaluation results for evaluation metric.
"""
info_str = []
with open(res_file, 'r') as fin:
preds = json.load(fin)
assert len(preds) == len(self.db)
outputs = []
gts = []
masks = []
box_sizes = []
for pred, item in zip(preds, self.db):
outputs.append(np.array(pred['keypoints'])[:, :-1])
gts.append(np.array(item['joints_3d'])[:, :-1])
masks.append((np.array(item['joints_3d_visible'])[:, 0]) > 0)
box_sizes.append(item['box_size'])
outputs = np.array(outputs)
gts = np.array(gts)
masks = np.array(masks)
box_sizes = np.array(box_sizes).reshape([-1, 1])
if 'NME' in metrics:
normalize_factor = self._get_normalize_factor(box_sizes)
info_str.append(
('NME', keypoint_nme(outputs, gts, masks, normalize_factor)))
return info_str
def _report_metric(self,
res_file,
metrics,
pck_thr=0.2,
pckh_thr=0.7,
auc_nor=30):
"""Keypoint evaluation.
Args:
res_file (str): Json file stored prediction results.
metrics (str | list[str]): Metric to be performed.
Options: 'PCK', 'PCKh', 'AUC', 'EPE', 'NME'.
pck_thr (float): PCK threshold, default as 0.2.
pckh_thr (float): PCKh threshold, default as 0.7.
auc_nor (float): AUC normalization factor, default as 30 pixel.
Returns:
List: Evaluation results for evaluation metric.
"""
info_str = []
with open(res_file, 'r') as fin:
preds = json.load(fin)
assert len(preds) == len(self.db)
outputs = []
gts = []
masks = []
box_sizes = []
threshold_bbox = []
threshold_head_box = []
for pred, item in zip(preds, self.db):
outputs.append(np.array(pred['keypoints'])[:, :-1])
gts.append(np.array(item['joints_3d'])[:, :-1])
masks.append((np.array(item['joints_3d_visible'])[:, 0]) > 0)
if 'PCK' in metrics:
bbox = np.array(item['bbox'])
bbox_thr = np.max(bbox[2:])
threshold_bbox.append(np.array([bbox_thr, bbox_thr]))
if 'PCKh' in metrics:
head_box_thr = item['head_size']
threshold_head_box.append(
np.array([head_box_thr, head_box_thr]))
box_sizes.append(item.get('box_size', 1))
outputs = np.array(outputs)
gts = np.array(gts)
masks = np.array(masks)
threshold_bbox = np.array(threshold_bbox)
threshold_head_box = np.array(threshold_head_box)
box_sizes = np.array(box_sizes).reshape([-1, 1])
if 'PCK' in metrics:
_, pck, _ = keypoint_pck_accuracy(outputs, gts, masks, pck_thr,
threshold_bbox)
info_str.append(('PCK', pck))
if 'PCKh' in metrics:
_, pckh, _ = keypoint_pck_accuracy(outputs, gts, masks, pckh_thr,
threshold_head_box)
info_str.append(('PCKh', pckh))
if 'AUC' in metrics:
info_str.append(('AUC', keypoint_auc(outputs, gts, masks,
auc_nor)))
if 'EPE' in metrics:
info_str.append(('EPE', keypoint_epe(outputs, gts, masks)))
if 'NME' in metrics:
normalize_factor = self._get_normalize_factor(gts=gts,
box_sizes=box_sizes)
info_str.append(
('NME', keypoint_nme(outputs, gts, masks, normalize_factor)))
return info_str
