in FasterRCNNDetection/utils/eval_tool.py [0:0]
def calc_detection_voc_prec_rec(
pred_bboxes, pred_labels, pred_scores, gt_bboxes, gt_labels,
gt_difficults=None,
iou_thresh=0.5):
"""Calculate precision and recall based on evaluation code of PASCAL VOC.
This function calculates precision and recall of
predicted bounding boxes obtained from a dataset which has :math:`N`
images.
The code is based on the evaluation code used in PASCAL VOC Challenge.
Args:
pred_bboxes (iterable of numpy.ndarray): An iterable of :math:`N`
sets of bounding boxes.
Its index corresponds to an index for the base dataset.
Each element of :obj:`pred_bboxes` is a set of coordinates
of bounding boxes. This is an array whose shape is :math:`(R, 4)`,
where :math:`R` corresponds
to the number of bounding boxes, which may vary among boxes.
The second axis corresponds to
:math:`y_{min}, x_{min}, y_{max}, x_{max}` of a bounding box.
pred_labels (iterable of numpy.ndarray): An iterable of labels.
Similar to :obj:`pred_bboxes`, its index corresponds to an
index for the base dataset. Its length is :math:`N`.
pred_scores (iterable of numpy.ndarray): An iterable of confidence
scores for predicted bounding boxes. Similar to :obj:`pred_bboxes`,
its index corresponds to an index for the base dataset.
Its length is :math:`N`.
gt_bboxes (iterable of numpy.ndarray): An iterable of ground truth
bounding boxes
whose length is :math:`N`. An element of :obj:`gt_bboxes` is a
bounding box whose shape is :math:`(R, 4)`. Note that the number of
bounding boxes in each image does not need to be same as the number
of corresponding predicted boxes.
gt_labels (iterable of numpy.ndarray): An iterable of ground truth
labels which are organized similarly to :obj:`gt_bboxes`.
gt_difficults (iterable of numpy.ndarray): An iterable of boolean
arrays which is organized similarly to :obj:`gt_bboxes`.
This tells whether the
corresponding ground truth bounding box is difficult or not.
By default, this is :obj:`None`. In that case, this function
considers all bounding boxes to be not difficult.
iou_thresh (float): A prediction is correct if its Intersection over
Union with the ground truth is above this value..
Returns:
tuple of two lists:
This function returns two lists: :obj:`prec` and :obj:`rec`.
* :obj:`prec`: A list of arrays. :obj:`prec[l]` is precision \
for class :math:`l`. If class :math:`l` does not exist in \
either :obj:`pred_labels` or :obj:`gt_labels`, :obj:`prec[l]` is \
set to :obj:`None`.
* :obj:`rec`: A list of arrays. :obj:`rec[l]` is recall \
for class :math:`l`. If class :math:`l` that is not marked as \
difficult does not exist in \
:obj:`gt_labels`, :obj:`rec[l]` is \
set to :obj:`None`.
"""
#print(pred_scores)
#print(len(pred_bboxes),len(pred_labels),len(pred_scores),len(gt_bboxes),len(gt_labels),len(gt_difficults))
pred_bboxes = iter(pred_bboxes)
pred_labels = iter(pred_labels)
pred_scores = iter(pred_scores)
gt_bboxes = iter(gt_bboxes)
gt_labels = iter(gt_labels)
gt_difficults = itertools.repeat(None) #need to figure out why gt_difficults is the wrong length
#if gt_difficults is None:
# gt_difficults = itertools.repeat(None)
#else:
# gt_difficults = iter(gt_difficults)
n_pos = defaultdict(int)
score = defaultdict(list)
match = defaultdict(list)
for pred_bbox, pred_label, pred_score, gt_bbox, gt_label, gt_difficult in \
six.moves.zip(
pred_bboxes, pred_labels, pred_scores,
gt_bboxes, gt_labels, gt_difficults):
if gt_difficult is None:
gt_difficult = np.zeros(len(gt_bbox), dtype=bool)
for l in np.unique(np.concatenate((pred_label, gt_label)).astype(int)):
pred_mask_l = pred_label == l
pred_bbox_l = pred_bbox[pred_mask_l]
pred_score_l = pred_score[pred_mask_l]
# sort by score
order = pred_score_l.argsort()[::-1]
pred_bbox_l = pred_bbox_l[order]
pred_score_l = pred_score_l[order]
gt_mask_l = [i for i in range(len(gt_label)) if gt_label[i] == l]
if len(gt_bbox) > 0:
gt_bbox_l = np.asarray([gt_bbox[i] for i in gt_mask_l])
else:
gt_bbox_l = []
gt_difficult_l = gt_difficult[gt_mask_l]
n_pos[l] += np.logical_not(gt_difficult_l).sum()
score[l].extend(pred_score_l)
if len(pred_bbox_l) == 0:
continue
if len(gt_bbox_l) == 0:
match[l].extend((0,) * pred_bbox_l.shape[0])
continue
# VOC evaluation follows integer typed bounding boxes.
pred_bbox_l = pred_bbox_l.copy()
pred_bbox_l[:, 2:] += 1
gt_bbox_l = gt_bbox_l.copy()
gt_bbox_l[:, 2:] += 1
iou = bbox_iou(pred_bbox_l, gt_bbox_l)
gt_index = iou.argmax(axis=1)
# set -1 if there is no matching ground truth
gt_index[iou.max(axis=1) < iou_thresh] = -1
del iou
#print(gt_index)
selec = np.zeros(gt_bbox_l.shape[0], dtype=bool)
for gt_idx in gt_index:
if gt_idx >= 0:
if gt_difficult_l[gt_idx]:
match[l].append(-1)
else:
if not selec[gt_idx]:
match[l].append(1)
else:
match[l].append(0)
selec[gt_idx] = True
else:
match[l].append(0)
for iter_ in (
pred_bboxes, pred_labels, pred_scores,
gt_bboxes, gt_labels, gt_difficults):
if next(iter_, None) is not None:
raise ValueError('Length of input iterables need to be same.')
n_fg_class = max(n_pos.keys()) + 1
prec = [None] * n_fg_class
rec = [None] * n_fg_class
for l in n_pos.keys():
score_l = np.array(score[l])
match_l = np.array(match[l], dtype=np.int8)
order = score_l.argsort()[::-1]
match_l = match_l[order]
tp = np.cumsum(match_l == 1)
fp = np.cumsum(match_l == 0)
# If an element of fp + tp is 0,
# the corresponding element of prec[l] is nan.
prec[l] = tp / (fp + tp)
# If n_pos[l] is 0, rec[l] is None.
if n_pos[l] > 0:
rec[l] = tp / n_pos[l]
#rec = [i.numpy() for i in rec if i is not None]
return prec, rec