def get_triplet_stats(split):
m = h5py.File('/media/zawlin/ssd/Dropbox/proj/sg_vrd_meta.h5')
triplets = {}
triplets_idx = {}
for imid in m['gt/%s/' % split].keys():
rlp_labels = m['gt/%s/%s/rlp_labels' % (split, imid)][...]
sub_boxes = m['gt/%s/%s/sub_boxes' % (split, imid)][...]
obj_boxes = m['gt/%s/%s/obj_boxes' % (split, imid)][...]
for i in xrange(rlp_labels.shape[0]):
p_idx = rlp_labels[i][1]
s_idx = rlp_labels[i][0]
o_idx = rlp_labels[i][2]
p_str = zl.idx2name_pre(m, p_idx)
s_str = zl.idx2name_cls(m, s_idx)
o_str = zl.idx2name_cls(m, o_idx)
sb = sub_boxes[i]
ob = obj_boxes[i]
#triplet = str(sub_cls_idx)+'_'+str(pre_idx)+'_'+str(obj_cls_idx)
triplet_idx = str(s_idx) + '_' + str(p_idx) + '_' + str(o_idx)
triplet = s_str + '_' + p_str + '_' + o_str
if triplet not in triplets:
triplets[triplet] = 0
if triplet_idx not in triplets_idx:
triplets_idx[triplet_idx] = 0
triplets[triplet] += 1
triplets_idx[triplet_idx] += 1
triplets_sorted = sorted(triplets.items(),
key=operator.itemgetter(1),
reverse=True)
triplets_idx_sorted = sorted(triplets_idx.items(),
key=operator.itemgetter(1),
reverse=True)
return triplets, triplets_sorted
def vr_make_meta_gt_visual_phrase():
m = h5py.File('data/sg_vrd_meta.h5','r',driver='core')
h5f = h5py.File('data/sg_vrd_vp_meta.h5')
triplets = {}
cnt = 0
zl.tick()
for k in m['gt/train'].keys():
if cnt %1000==0:
print cnt,zl.tock()
zl.tick()
cnt+=1
gt_boxes = []
gt_labels = []
sub_boxes = m['gt/train/%s/sub_boxes'%k][...]
obj_boxes = m['gt/train/%s/obj_boxes'%k][...]
rlp_labels = m['gt/train/%s/rlp_labels'%k][...]
for i in xrange(rlp_labels.shape[0]):
sub_box = sub_boxes[i]
obj_box = obj_boxes[i]
rlp_label = rlp_labels[i]
joint_box = [min(sub_box[0],obj_box[0]), min(sub_box[1],obj_box[1]),max(sub_box[2],obj_box[2]),max(sub_box[3],obj_box[3])]
s_lbl = zl.idx2name_cls(m,rlp_label[0])
o_lbl = zl.idx2name_cls(m,rlp_label[2])
p_lbl = zl.idx2name_pre(m,rlp_label[1])
spo = '%s_%s_%s'%(s_lbl,p_lbl,o_lbl)
lbl = zl.name2idx_tri(h5f,spo)
gt_boxes.append(joint_box)
gt_labels.append(lbl)
h5f.create_dataset('gt/train/%s/labels'%k,data = np.array(gt_labels).astype(np.int16))
h5f.create_dataset('gt/train/%s/boxes'%k,data = np.array(gt_boxes).astype(np.int16))
def visualize_gt_data():
m = h5py.File('/media/zawlin/ssd/Dropbox/proj/sg_vrd_meta.h5')
split = 'test'
triplets = {}
root = 'data/sg_vrd_2016/Data/sg_%s_images/' % split
for imid in m['gt/%s/' % split].keys():
im_path = root + imid + '.jpg'
im = cv2.imread(im_path)
rlp_labels = m['gt/%s/%s/rlp_labels' % (split, imid)][...]
sub_boxes = m['gt/%s/%s/sub_boxes' % (split, imid)][...]
obj_boxes = m['gt/%s/%s/obj_boxes' % (split, imid)][...]
for i in xrange(rlp_labels.shape[0]):
p_idx = rlp_labels[i][1]
s_idx = rlp_labels[i][0]
o_idx = rlp_labels[i][2]
p_str = zl.idx2name_pre(m, p_idx)
s_str = zl.idx2name_cls(m, s_idx)
o_str = zl.idx2name_cls(m, o_idx)
sb = sub_boxes[i]
ob = obj_boxes[i]
cv2.rectangle(im, (sb[0], sb[1]), (sb[2], sb[3]), (0, 200, 0), 2)
cv2.rectangle(im, (ob[0], ob[1]), (ob[2], ob[3]), (0, 0, 200), 2)
#triplet = str(sub_cls_idx)+'_'+str(pre_idx)+'_'+str(obj_cls_idx)
triplet = s_str + '_' + p_str + '_' + o_str
print triplet
if triplet not in triplets:
triplets[triplet] = 0
triplets[triplet] += 1
cv2.imshow('im', im)
c = cv2.waitKey(0) & 0xFF
if c == 27:
exit(0)
def vg_make_meta_visual_phrase():
m = h5py.File('data/vg1_2_meta.h5', 'r', driver='core')
h5f = h5py.File('data/vg1_2_vp_meta.h5')
triplets = {}
cnt = 0
zl.tick()
for k in m['gt/train'].keys():
if cnt % 1000 == 0:
print cnt, zl.tock()
zl.tick()
cnt += 1
# sub_boxes = m['gt/train/%s/sub_boxes'%k][...]
# obj_boxes = m['gt/train/%s/obj_boxes'%k][...]
rlp_labels = m['gt/train/%s/rlp_labels' % k][...]
for i in xrange(rlp_labels.shape[0]):
# sub_box = sub_boxes[i]
# obj_box = obj_boxes[i]
rlp_label = rlp_labels[i]
# joint_bbox = [min(sub_bbox[0],obj_bbox[0]), min(sub_bbox[1],obj_bbox[1]),max(sub_bbox[2],obj_bbox[2]),max(sub_bbox[3],obj_bbox[3])]
s_lbl = zl.idx2name_cls(m, rlp_label[0])
o_lbl = zl.idx2name_cls(m, rlp_label[2])
p_lbl = zl.idx2name_pre(m, rlp_label[1])
spo = '%s_%s_%s' % (s_lbl, p_lbl, o_lbl)
# spo = '%d_%d_%d'%(rlp_label[0],rlp_label[1],rlp_label[2])
if spo not in triplets:
triplets[spo] = 0
triplets[spo] += 1
zl.save('output/pkl/triplets_train_vp.pkl', triplets)
triplets_sorted = zl.sort_dict_by_val(triplets)
triplets_ok = []
for k, v in triplets_sorted:
triplets_ok.append(k)
print k, v
triplets_ok = sorted(triplets_ok)
triplets_ok = ['__background__'] + triplets_ok
for i in xrange(len(triplets_ok)):
h5f['meta/tri/idx2name/%d' % i] = triplets_ok[i]
h5f['meta/tri/name2idx/%s' % triplets_ok[i]] = i
print len(triplets_ok)
def run_retrieval_vp_v2():
# h5_path = 'output/sg_vrd_2016_result.classeme.hdf5'
h5_path = 'output/precalc/vg1_2_vp2016_test_nms2_.4.hdf5'
m = h5py.File('/home/zawlin/Dropbox/proj/vg1_2_meta.h5', 'r', 'core')
m_vp = h5py.File('/home/zawlin/Dropbox/proj/vg1_2_vp_meta.h5', 'r', 'core')
cache_path = 'output/cache/%s.pkl' % h5_path.split('/')[-1]
data_root = '/home/zawlin/data/data_vrd/vg_1.2/'
rlp_map = []
for i in xrange(1, len(m_vp['meta/tri/idx2name'].keys())):
tri = str(m_vp['meta/tri/idx2name'][str(i)][...])
s_lbl = tri.split('_')[0]
p_lbl = tri.split('_')[1]
o_lbl = tri.split('_')[2]
rlp_label = [
zl.name2idx_cls(m, s_lbl),
zl.name2idx_pre(m, p_lbl),
zl.name2idx_cls(m, o_lbl)
]
rlp_map.append(rlp_label)
rlp_map = np.array(rlp_map)
if os.path.exists(cache_path):
print 'load from cache'
h5f = zl.load(cache_path)
else:
h5_in = h5py.File(h5_path, 'r')
h5f = {}
print 'preloading data'
for i in h5_in:
h5f[i] = {}
h5f[i]['labels'] = h5_in[i]['labels'][...]
h5f[i]['confs'] = h5_in[i]['confs'][...]
h5f[i]['boxes'] = h5_in[i]['boxes'][...]
zl.save(cache_path, h5f)
print 'preloading data done'
retr_meta = zl.load('output/pkl/vg_retr_meta.pkl')
thresh = 0.0
images = {}
imids = h5f.keys()
results = {}
cnt = 0
r_acc_100 = 0
r_acc_50 = 0
tp_total = 0
gt_total = 0
median = []
total = 0
retr_meta = zl.load('output/pkl/vg_retr_meta.pkl')
for k in xrange(len(retr_meta['rlp_labels'])):
total += retr_meta['counts'][k]
if k > 1000:
print total / 1000.
exit(0)
break
continue
cnt += 1
rlp_label = retr_meta['rlp_labels'][k]
gt_files = retr_meta['files'][k]
# print gt_files
# exit(0)
# for f in gt_files:
# impath= zl.imid2path(m,f)
# print impath
# im= cv2.imread(data_root+impath)
# cv2.imshow('im',im)
# cv2.waitKey(0)
results = {}
zl.tick()
ranks = []
for imid in imids:
labels = h5f[imid]['labels'] - 1
rlp_confs = h5f[imid]['confs']
rlp_labels = rlp_map[labels]
if rlp_labels.shape[0] == 0:
results[imid] = 0.0
continue
indexor = np.arange(rlp_labels.shape[0])
ind = indexor[np.all(rlp_labels == rlp_label, axis=1)]
if ind.shape[0] == 0:
results[imid] = 0.0
continue
confs = rlp_confs[ind]
results[imid] = np.average(confs)
results_sorted = zl.sort_dict_by_val(results)
total_gt = len(gt_files) + 0.0
gt_total += total_gt + 0.0
tp_50 = 0.
tp_100 = 0.
found = False
s_lbl = zl.idx2name_cls(m, rlp_label[0])
p_lbl = zl.idx2name_pre(m, rlp_label[1])
o_lbl = zl.idx2name_cls(m, rlp_label[2])
lbl_str = '%s_%s_%s' % (s_lbl, p_lbl, o_lbl)
delay = 0
for i in xrange(len(results_sorted)):
imid, v = results_sorted[i]
impath = zl.imid2path(m, imid)
if found and i >= 5:
break
# print gt_files
cor = imid in gt_files
if cor:
if not found:
found = True
median.append(i)
if i < 5:
tp_100 += 1
tp_total += 1
if i < 50: tp_50 += 1
# if True:
# cor_or_not = str(cor)
# if cor :delay=0
# if delay ==0:
# im = cv2.imread(data_root+impath)
# cv2.putText(im, cor_or_not, (50, 50), cv2.FONT_HERSHEY_COMPLEX, 1, (0, 0, 255), 1)
# cv2.putText(im, lbl_str, (50, 80), cv2.FONT_HERSHEY_COMPLEX, 1, (0, 0, 255), 1)
# cv2.putText(im, str(i), (50, 100), cv2.FONT_HERSHEY_COMPLEX, 1, (0, 0, 255), 1)
# cv2.imshow('im',im)
# c = cv2.waitKey(delay)&0xFF
# if c ==27:
# exit(0)
# if c == ord('s'):
# delay = 1-delay
# if c == ord('c'):
# delay = 1
r_50 = tp_50 / 5 #total_gt
r_100 = tp_100 / 5 #total_gt
r_acc_50 += r_50
r_acc_100 += r_100
med = np.median(median)
print '%d %f %f %f %f %d %f' % (cnt, r_50, r_100, r_acc_50 / cnt,
r_acc_100 / cnt, med, zl.tock())
def run():
prototxt = 'models/sg_vrd/rel_iccv/test_iccv_gt.prototxt'
obj_detector_model='data/models/vrd_rfcn/vrd_resnet50_rfcn_iter_70000.caffemodel'
relation_model='output/sg_vrd_rfcn/psroi_context_tri_sum_cached_iter_75500.caffemodel'
caffe.set_mode_gpu()
caffe.set_device(0)
net = caffe.Net(prototxt, caffe.TEST)
net.copy_from(obj_detector_model)
net.copy_from(relation_model)
m = h5py.File('/home/zawlin/Dropbox/proj/sg_vrd_meta.h5', 'r')
cnt = 0
root_img = '/home/zawlin/Dropbox/iccv17_hw/_results_from_zl/img/'
root_cls = '/home/zawlin/Dropbox/iccv17_hw/_results_from_zl/cls/'
import glog
for k in m['gt/test'].keys():
if not os.path.exists(root_img+k):
os.makedirs(root_img+k)
cnt += 1
glog.info(cnt)
if cnt >80:
break
rlp_labels = m['gt/test/%s/rlp_labels'%k][...]
sub_boxes = m['gt/test/%s/sub_boxes'%k][...].astype(np.float)
obj_boxes = m['gt/test/%s/obj_boxes'%k][...].astype(np.float)
if sub_boxes.shape[0]>0:
zeros = np.zeros((sub_boxes.shape[0],1), dtype=np.float)
# first index is always zero since we do one image by one image
sub_boxes = np.concatenate((zeros, sub_boxes),axis=1)
obj_boxes = np.concatenate((zeros, obj_boxes),axis=1)
im_path = C.get_sg_vrd_path_test(k)
im = cv2.imread(im_path)
for i in xrange(sub_boxes.shape[0]):
# sb = sub_boxes[i][1:].astype(np.int)
# ob = obj_boxes[i][1:].astype(np.int)
rlp = rlp_labels[i]
rel = zl.idx2name_cls(m,rlp[0])+' '+zl.idx2name_pre(m,rlp[1])+' '+zl.idx2name_cls(m,rlp[2])
x1,y1,x2,y2 = union(sub_boxes[i][1:],obj_boxes[i][1:])
cv2.rectangle(im,(x1,y1),(x2,y2),(255,0,0),2)
cv2.putText(im,rel,(x1,y1),cv2.FONT_HERSHEY_SIMPLEX,1.0,(0,0,255),2)
# cv2.rectangle(im,(sb[0],sb[1]),(sb[2],sb[3]),(255,0,0),2)
# cv2.rectangle(im,(ob[0],ob[1]),(ob[2],ob[3]),(255,0,0),2)
cv2.imshow('im',im)
cv2.imwrite(root_img+k+'/_.orig.jpg',im)
im_detect(net,im_path,sub_boxes,obj_boxes)
rfcn_sub_rel = net.blobs['rfcn_sub_rel'].data[0]
rfcn_obj_rel = net.blobs['rfcn_obj_rel'].data[0]
rfcn_union_rel = net.blobs['rfcn_union_rel'].data[0]
for pi in xrange(70):
index = pi
head, last = index * 9, (index + 1)*9
feat_sub = rfcn_sub_rel[head:last]
feat_obj= rfcn_obj_rel[head:last]
feat_union= rfcn_union_rel[head:last]
im_vis_sub = get_vis(feat_sub)
im_vis_obj = get_vis(feat_obj)
im_vis_union = get_vis(feat_union)
pre = zl.idx2name_pre(m,pi)
cv2.imwrite(root_img+k+'/%s_sub.jpg'%pre,im_vis_sub)
cv2.imwrite(root_img+k+'/%s_obj.jpg'%pre,im_vis_obj)
cv2.imwrite(root_img+k+'/%s_union.jpg'%pre,im_vis_union)
if not os.path.exists(root_cls+pre):
os.makedirs(root_cls+pre)
cv2.imwrite(root_cls+pre+'/%s_sub.jpg'%k,im_vis_sub)
cv2.imwrite(root_cls+pre+'/%s_obj.jpg'%k,im_vis_obj)
cv2.imwrite(root_cls+pre+'/%s_union.jpg'%k,im_vis_union)
#cv2.imshow(pre+'sub',im_vis_sub)
#cv2.imshow(pre+'obj',im_vis_obj)
#cv2.imshow(pre+'union',im_vis_union)
#if cv2.waitKey(0)==27:
# exit(0)
else:
#todo
#print nothing
pass
cv2.waitKey(0)
def run_retrieval_zeroshot():
# h5_path = 'output/sg_vrd_2016_result_all_19500.hdf5'
# h5_path = 'output/sg_vrd_2016_result_diff_all_5000.hdf5'
# h5_path= 'output/results/lu_method_results.hdf5'
# h5_path = 'output/sg_vrd_2016_result.hdf5.dd'
# h5_path = 'output/results/lu_method_results_max.hdf5'
h5_path = 'output/results/lu_visual_method_results.hdf5'
data_root = 'data/sg_vrd_2016/Data/sg_test_images/'
m = h5py.File('/home/zawlin/Dropbox/proj/sg_vrd_meta.h5', 'r', 'core')
zeroshots = m['meta/zeroshots'][...]
gt_cache_path = 'output/cache/sg_vrd_gt_cache.pkl'
gt_h5f = {}
np.random.seed(76)
if os.path.exists(gt_cache_path):
print 'load gt from cache'
gt_h5f = zl.load(gt_cache_path)
else:
print 'cacheing gt'
for k in m['gt/test']:
gt_h5f[k] = {}
sub_boxes = m['gt/test'][k]['sub_boxes'][...]
rlp_labels = m['gt/test'][k]['rlp_labels'][...]
obj_boxes = m['gt/test'][k]['obj_boxes'][...]
gt_h5f[k]['sub_boxes'] = sub_boxes
gt_h5f[k]['obj_boxes'] = obj_boxes
gt_h5f[k]['rlp_labels'] = rlp_labels
print 'caching gt done'
zl.save(gt_cache_path, gt_h5f)
cache_path = 'output/cache/%s.pkl' % h5_path.split('/')[-1]
# h5f = h5py.File('output/sg_vrd_2016_result.classeme.hdf5')
if os.path.exists(cache_path):
print 'load from cache'
h5f = zl.load(cache_path)
else:
h5_in = h5py.File(h5_path, 'r')
h5f = {}
print 'preloading data'
for i in h5_in:
h5f[i] = {}
h5f[i]['rlp_labels'] = h5_in[i]['rlp_labels'][...]
h5f[i]['rlp_confs'] = h5_in[i]['rlp_confs'][...]
h5f[i]['sub_boxes'] = h5_in[i]['sub_boxes'][...]
h5f[i]['obj_boxes'] = h5_in[i]['obj_boxes'][...]
zl.save(cache_path, h5f)
print 'preloading data done'
#h5f = h5py.file('output/results/lu_method_results.hdf5')
retr_meta = zl.load('output/pkl/vr_retr_meta.pkl')
thresh = 0.0
images = {}
imids = h5f.keys()
results = {}
cnt = 0
r_acc_100 = 0
r_acc_50 = 0
tp_total = 0
gt_total = 0
median = []
for k in xrange(len(retr_meta['rlp_labels'])):
# if k>1000:
# break
rlp_label = retr_meta['rlp_labels'][k]
if not np.any(np.all(zeroshots == rlp_label, axis=1)): continue
gt_files = retr_meta['files'][k]
cnt += 1
results = {}
zl.tic()
for imid in imids:
rlp_labels = h5f[imid]['rlp_labels']
rlp_confs = h5f[imid]['rlp_confs']
if rlp_confs.shape[0] == 0:
results[imid] = 0.0
continue
indexor = np.arange(rlp_labels.shape[0])
ind = indexor[np.all(rlp_labels == rlp_label, axis=1)]
if ind.shape[0] == 0:
results[imid] = 0.0
continue
confs = rlp_confs[ind]
results[imid] = np.random.uniform(-1, 1) #np.average(confs)
results_sorted = zl.sort_dict_by_val(results)
total_gt = len(gt_files) + 0.0
gt_total += total_gt + 0.0
tp_50 = 0.
tp_100 = 0.
found = False
delay = 0
s_lbl = zl.idx2name_cls(m, rlp_label[0])
p_lbl = zl.idx2name_pre(m, rlp_label[1])
o_lbl = zl.idx2name_cls(m, rlp_label[2])
lbl_str = '%s_%s_%s' % (s_lbl, p_lbl, o_lbl)
r_at_k = 5
for i in xrange(len(results_sorted)):
imid, v = results_sorted[i]
if found and i >= r_at_k:
break
cor = imid in gt_files
if cor:
if not found:
found = True
median.append(i)
if i < r_at_k:
tp_100 += 1
tp_total += 1
if i < 50: tp_50 += 1
# if True:
# cor_or_not = str(cor)
# if cor :delay=0
# if delay ==0:
# im = cv2.imread(data_root+imid+'.jpg')
# cv2.putText(im, cor_or_not, (50, 50), cv2.FONT_HERSHEY_COMPLEX, 1, (0, 0, 255), 1)
# cv2.putText(im, lbl_str, (50, 80), cv2.FONT_HERSHEY_COMPLEX, 1, (0, 0, 255), 1)
# cv2.putText(im, str(i), (50, 100), cv2.FONT_HERSHEY_COMPLEX, 1, (0, 0, 255), 1)
# cv2.imshow('im',im)
# c = cv2.waitKey(delay)&0xFF
# if c ==27:
# exit(0)
# if c == ord('s'):
# delay = 1-delay
# if c == ord('c'):
# delay = 1
r_50 = tp_50 / r_at_k #total_gt
r_100 = tp_100 / r_at_k #total_gt
r_acc_50 += r_50
r_acc_100 += r_100
med = np.median(median)
print '%d %f %f %f %f %d %f' % (cnt, r_50, r_100, r_acc_50 / cnt,
r_acc_100 / cnt, med, zl.toc())
def gen_meta_for_retrieval():
out_pkl = 'output/pkl/vr_retr_meta.pkl'
m = h5py.File('/home/zawlin/Dropbox/proj/sg_vrd_meta.h5', 'r')
data_root = 'data/sg_vrd_2016/Data/sg_test_images/'
rlp_labels = []
files = []
counts = []
sub_boxes = []
obj_boxes = []
for k in m['gt/test']:
gt_rlp_labels = m['gt/test'][k]['rlp_labels'][...]
gt_sub_boxes = m['gt/test'][k]['sub_boxes'][...]
gt_obj_boxes = m['gt/test'][k]['obj_boxes'][...]
for i in xrange(gt_rlp_labels.shape[0]):
gt_rlp_label = gt_rlp_labels[i]
gt_sub_box = gt_sub_boxes[i]
gt_obj_box = gt_obj_boxes[i]
if len(rlp_labels) == 0:
rlp_labels.append(gt_rlp_label.tolist())
files.append([k])
sub_boxes.append([gt_sub_box.tolist()])
obj_boxes.append([gt_obj_box.tolist()])
counts.append(1)
continue
bInd = np.all(gt_rlp_label == rlp_labels, axis=1)
ind = np.arange(len(rlp_labels))[bInd]
if len(ind) == 0:
rlp_labels.append(gt_rlp_label.tolist())
files.append([k])
counts.append(1)
sub_boxes.append([gt_sub_box.tolist()])
obj_boxes.append([gt_obj_box.tolist()])
else:
files[ind].append(k)
counts[ind] = counts[ind] + 1
sub_boxes[ind].append(gt_sub_box.tolist())
obj_boxes[ind].append(gt_obj_box.tolist())
# rlp_labels.append(gt_rlp_label.tolist())
# files.append([k])
# counts.append(1)
rlp_labels = np.array(rlp_labels)
files = np.array(files)
counts = np.array(counts)
sub_boxes = np.array(sub_boxes)
obj_boxes = np.array(obj_boxes)
ind = np.argsort(counts)[::-1]
counts = counts[ind]
files = files[ind]
rlp_labels = rlp_labels[ind]
sub_boxes = sub_boxes[ind]
obj_boxes = obj_boxes[ind]
print sub_boxes[:4]
for i in xrange(20):
rlp_label = rlp_labels[i]
print files[i]
s_lbl = zl.idx2name_cls(m, rlp_label[0])
p_lbl = zl.idx2name_pre(m, rlp_label[1])
o_lbl = zl.idx2name_cls(m, rlp_label[2])
print s_lbl, p_lbl, o_lbl
for j in xrange(len(files[i])):
s_box = sub_boxes[i][j]
o_box = obj_boxes[i][j]
fpath = files[i][j]
impath = data_root + fpath + '.jpg'
im = cv2.imread(impath)
cv2.rectangle(im, (s_box[0], s_box[1]), (s_box[2], s_box[3]),
(0, 255, 0), 1)
cv2.rectangle(im, (o_box[0], o_box[1]), (o_box[2], o_box[3]),
(255, 0, 0), 1)
cv2.imshow('im', im)
cv2.waitKey(0)
retr_meta = {
'counts': counts,
'files': files,
'rlp_labels': rlp_labels,
'sub_boxes': sub_boxes,
'obj_boxes': obj_boxes
}
zl.save(out_pkl, retr_meta)