in detectron/datasets/densepose_cocoeval.py [0:0]
def evaluateImg(self, imgId, catId, aRng, maxDet):
'''
perform evaluation for single category and image
:return: dict (single image results)
'''
p = self.params
if p.useCats:
gt = self._gts[imgId,catId]
dt = self._dts[imgId,catId]
else:
gt = [_ for cId in p.catIds for _ in self._gts[imgId,cId]]
dt = [_ for cId in p.catIds for _ in self._dts[imgId,cId]]
if len(gt) == 0 and len(dt) == 0:
return None
for g in gt:
#g['_ignore'] = g['ignore']
if g['ignore'] or (g['area']<aRng[0] or g['area']>aRng[1]):
g['_ignore'] = True
else:
g['_ignore'] = False
# sort dt highest score first, sort gt ignore last
gtind = np.argsort([g['_ignore'] for g in gt], kind='mergesort')
gt = [gt[i] for i in gtind]
dtind = np.argsort([-d['score'] for d in dt], kind='mergesort')
dt = [dt[i] for i in dtind[0:maxDet]]
iscrowd = [int(o['iscrowd']) for o in gt]
# load computed ious
if p.iouType == 'uv':
#print('Checking the length', len(self.ious[imgId, catId]))
#if len(self.ious[imgId, catId]) == 0:
# print(self.ious[imgId, catId])
ious = self.ious[imgId, catId][0][:, gtind] if len(self.ious[imgId, catId]) > 0 else self.ious[imgId, catId]
ioubs = self.ious[imgId, catId][1][:, gtind] if len(self.ious[imgId, catId]) > 0 else self.ious[imgId, catId]
else:
ious = self.ious[imgId, catId][:, gtind] if len(self.ious[imgId, catId]) > 0 else self.ious[imgId, catId]
T = len(p.iouThrs)
G = len(gt)
D = len(dt)
gtm = np.zeros((T,G))
dtm = np.zeros((T,D))
gtIg = np.array([g['_ignore'] for g in gt])
dtIg = np.zeros((T,D))
if np.all(gtIg) == True and p.iouType == 'uv':
dtIg = np.logical_or(dtIg, True)
if len(ious)>0: # and not p.iouType == 'uv':
for tind, t in enumerate(p.iouThrs):
for dind, d in enumerate(dt):
# information about best match so far (m=-1 -> unmatched)
iou = min([t,1-1e-10])
m = -1
for gind, g in enumerate(gt):
# if this gt already matched, and not a crowd, continue
if gtm[tind,gind]>0 and not iscrowd[gind]:
continue
# if dt matched to reg gt, and on ignore gt, stop
if m>-1 and gtIg[m]==0 and gtIg[gind]==1:
break
# continue to next gt unless better match made
if ious[dind,gind] < iou:
continue
if ious[dind,gind] == 0.:
continue
# if match successful and best so far, store appropriately
iou = ious[dind, gind]
m = gind
# if match made store id of match for both dt and gt
if m == -1:
continue
dtIg[tind, dind] = gtIg[m]
dtm[tind, dind] = gt[m]['id']
gtm[tind, m] = d['id']
if p.iouType == 'uv':
if not len(ioubs)==0:
for dind, d in enumerate(dt):
# information about best match so far (m=-1 -> unmatched)
if dtm[tind, dind] == 0:
ioub = 0.8
m = -1
for gind, g in enumerate(gt):
# if this gt already matched, and not a crowd, continue
if gtm[tind,gind]>0 and not iscrowd[gind]:
continue
# continue to next gt unless better match made
if ioubs[dind,gind] < ioub:
continue
# if match successful and best so far, store appropriately
ioub = ioubs[dind,gind]
m = gind
# if match made store id of match for both dt and gt
if m > -1:
dtIg[:, dind] = gtIg[m]
if gtIg[m]:
dtm[tind, dind] = gt[m]['id']
gtm[tind, m] = d['id']
# set unmatched detections outside of area range to ignore
a = np.array([d['area']<aRng[0] or d['area']>aRng[1] for d in dt]).reshape((1, len(dt)))
dtIg = np.logical_or(dtIg, np.logical_and(dtm==0, np.repeat(a,T,0)))
# store results for given image and category
#print('Done with the function', len(self.ious[imgId, catId]))
return {
'image_id': imgId,
'category_id': catId,
'aRng': aRng,
'maxDet': maxDet,
'dtIds': [d['id'] for d in dt],
'gtIds': [g['id'] for g in gt],
'dtMatches': dtm,
'gtMatches': gtm,
'dtScores': [d['score'] for d in dt],
'gtIgnore': gtIg,
'dtIgnore': dtIg,
}