in example/rcnn/rcnn/dataset/pascal_voc_eval.py [0:0]
def voc_eval(detpath, annopath, imageset_file, classname, annocache, ovthresh=0.5, use_07_metric=False):
"""
pascal voc evaluation
:param detpath: detection results detpath.format(classname)
:param annopath: annotations annopath.format(classname)
:param imageset_file: text file containing list of images
:param classname: category name
:param annocache: caching annotations
:param ovthresh: overlap threshold
:param use_07_metric: whether to use voc07's 11 point ap computation
:return: rec, prec, ap
"""
with open(imageset_file, 'r') as f:
lines = f.readlines()
image_filenames = [x.strip() for x in lines]
# load annotations from cache
if not os.path.isfile(annocache):
recs = {}
for ind, image_filename in enumerate(image_filenames):
recs[image_filename] = parse_voc_rec(annopath.format(image_filename))
if ind % 100 == 0:
logger.info('reading annotations for %d/%d' % (ind + 1, len(image_filenames)))
logger.info('saving annotations cache to %s' % annocache)
with open(annocache, 'wb') as f:
cPickle.dump(recs, f, protocol=cPickle.HIGHEST_PROTOCOL)
else:
with open(annocache, 'rb') as f:
recs = cPickle.load(f)
# extract objects in :param classname:
class_recs = {}
npos = 0
for image_filename in image_filenames:
objects = [obj for obj in recs[image_filename] if obj['name'] == classname]
bbox = np.array([x['bbox'] for x in objects])
difficult = np.array([x['difficult'] for x in objects]).astype(np.bool)
det = [False] * len(objects) # stand for detected
npos = npos + sum(~difficult)
class_recs[image_filename] = {'bbox': bbox,
'difficult': difficult,
'det': det}
# read detections
detfile = detpath.format(classname)
with open(detfile, 'r') as f:
lines = f.readlines()
splitlines = [x.strip().split(' ') for x in lines]
image_ids = [x[0] for x in splitlines]
confidence = np.array([float(x[1]) for x in splitlines])
bbox = np.array([[float(z) for z in x[2:]] for x in splitlines])
# sort by confidence
if bbox.shape[0] > 0:
sorted_inds = np.argsort(-confidence)
sorted_scores = np.sort(-confidence)
bbox = bbox[sorted_inds, :]
image_ids = [image_ids[x] for x in sorted_inds]
# go down detections and mark true positives and false positives
nd = len(image_ids)
tp = np.zeros(nd)
fp = np.zeros(nd)
for d in range(nd):
r = class_recs[image_ids[d]]
bb = bbox[d, :].astype(float)
ovmax = -np.inf
bbgt = r['bbox'].astype(float)
if bbgt.size > 0:
# compute overlaps
# intersection
ixmin = np.maximum(bbgt[:, 0], bb[0])
iymin = np.maximum(bbgt[:, 1], bb[1])
ixmax = np.minimum(bbgt[:, 2], bb[2])
iymax = np.minimum(bbgt[:, 3], bb[3])
iw = np.maximum(ixmax - ixmin + 1., 0.)
ih = np.maximum(iymax - iymin + 1., 0.)
inters = iw * ih
# union
uni = ((bb[2] - bb[0] + 1.) * (bb[3] - bb[1] + 1.) +
(bbgt[:, 2] - bbgt[:, 0] + 1.) *
(bbgt[:, 3] - bbgt[:, 1] + 1.) - inters)
overlaps = inters / uni
ovmax = np.max(overlaps)
jmax = np.argmax(overlaps)
if ovmax > ovthresh:
if not r['difficult'][jmax]:
if not r['det'][jmax]:
tp[d] = 1.
r['det'][jmax] = 1
else:
fp[d] = 1.
else:
fp[d] = 1.
# compute precision recall
fp = np.cumsum(fp)
tp = np.cumsum(tp)
rec = tp / float(npos)
# avoid division by zero in case first detection matches a difficult ground ruth
prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)
ap = voc_ap(rec, prec, use_07_metric)
return rec, prec, ap