in mask2former_video/data_video/datasets/ytvis_api/ytvoseval.py [0:0]
def computeOks(self, imgId, catId):
p = self.params
# dimention here should be Nxm
gts = self._gts[imgId, catId]
dts = self._dts[imgId, catId]
inds = np.argsort([-d['score'] for d in dts], kind='mergesort')
dts = [dts[i] for i in inds]
if len(dts) > p.maxDets[-1]:
dts = dts[0:p.maxDets[-1]]
# if len(gts) == 0 and len(dts) == 0:
if len(gts) == 0 or len(dts) == 0:
return []
ious = np.zeros((len(dts), len(gts)))
sigmas = np.array([.26, .25, .25, .35, .35, .79, .79, .72, .72, .62,.62, 1.07, 1.07, .87, .87, .89, .89])/10.0
vars = (sigmas * 2)**2
k = len(sigmas)
# compute oks between each detection and ground truth object
for j, gt in enumerate(gts):
# create bounds for ignore regions(double the gt bbox)
g = np.array(gt['keypoints'])
xg = g[0::3]; yg = g[1::3]; vg = g[2::3]
k1 = np.count_nonzero(vg > 0)
bb = gt['bbox']
x0 = bb[0] - bb[2]; x1 = bb[0] + bb[2] * 2
y0 = bb[1] - bb[3]; y1 = bb[1] + bb[3] * 2
for i, dt in enumerate(dts):
d = np.array(dt['keypoints'])
xd = d[0::3]; yd = d[1::3]
if k1>0:
# measure the per-keypoint distance if keypoints visible
dx = xd - xg
dy = yd - yg
else:
# measure minimum distance to keypoints in (x0,y0) & (x1,y1)
z = np.zeros((k))
dx = np.max((z, x0-xd),axis=0)+np.max((z, xd-x1),axis=0)
dy = np.max((z, y0-yd),axis=0)+np.max((z, yd-y1),axis=0)
e = (dx**2 + dy**2) / vars / (gt['avg_area']+np.spacing(1)) / 2
if k1 > 0:
e=e[vg > 0]
ious[i, j] = np.sum(np.exp(-e)) / e.shape[0]
return ious