def vr_vphrase_make_voc_format(split_type):
if split_type != 'train' and split_type != 'test':
print 'error'
exit(0)
m = h5py.File('/home/zawlin/Dropbox/proj/sg_vrd_meta.h5')
m_vp = h5py.File('/home/zawlin/Dropbox/proj/sg_vrd_vphrase_meta.h5')
root = '/home/zawlin/data/data_vrd/vrd/sg_vp/'
anno_root = root + 'Annotations/' + split_type + '/'
data_root = root + 'Data/' + split_type + '/'
zl.make_dirs(anno_root)
zl.make_dirs(data_root)
cnt = 0
zl.tick()
for k in m_vp['gt/%s' % split_type].keys():
if cnt % 1000 == 0:
print cnt, zl.tock()
zl.tick()
cnt += 1
# todo for vg
# im_data= db.image_data.find_one({'image_id':imid})
# im_path_full = im_data['url'].replace('https://cs.stanford.edu/people/rak248/','')
# im_path_folder = im_path_full.split('/')[0]
# im_path_file = im_path_full.split('/')[1]
# im_src_path = vr_root+'%s/%s'%(im_path_folder,im_path_file)
# im_dst_path = data_root+'%s/%s'%(im_path_folder,im_path_file)
# zl.copy_file(im_src_path,im_dst_path)
voc_datum = {
"folder": '',
"source": {
"database": "sg vrd visual phrase"
},
"filename": k + '.jpg'
}
m['train/%s/w' % k][...]
w, h = int(m['train/%s/w' % k][...]), int(m['train/%s/h' % k][...])
voc_datum['size'] = {'width': w, 'height': h}
objs = []
gt_boxes = m_vp['gt/%s/%s/boxes' % (split_type, k)][...]
gt_labels = m_vp['gt/%s/%s/labels' % (split_type, k)][...]
for i in xrange(gt_boxes.shape[0]):
gt_box = gt_boxes[i]
gt_label = gt_labels[i]
ymin, ymax, xmin, xmax = gt_box[1], gt_box[3], gt_box[0], gt_box[2]
bbox = {'ymin': ymin, 'ymax': ymax, 'xmin': xmin, 'xmax': xmax}
name = zl.idx2name_tri(m_vp, gt_label)
obj = {'name': name, 'bndbox': bbox}
objs.append(obj)
voc_datum['object'] = objs
#write to xml
dst_path = os.path.join(
anno_root, voc_datum["folder"],
voc_datum["filename"][:voc_datum["filename"].rfind('.')] + '.xml')
voc_datum = {'annotation': voc_datum}
f = open(dst_path, 'w')
f.write(dict2xml(voc_datum) + '\n')
f.close()
print 'images with annotation=%d\n' % cnt
def vr_vphrase_make_voc_format(split_type):
if split_type !='train' and split_type!='test':
print 'error'
exit(0)
m = h5py.File('data/sg_vrd_meta.h5')
m_vp = h5py.File('data/sg_vrd_vphrase_meta.h5')
root = 'data/sg_vrd_2016_vp/'
anno_root= root+'Annotations/'+split_type+'/'
data_root= root+'Data/'+split_type+'/'
zl.make_dirs(anno_root)
zl.make_dirs(data_root)
cnt = 0
zl.tick()
for k in m_vp['gt/%s'%split_type].keys():
if cnt%1000==0:
print cnt,zl.tock()
zl.tick()
cnt+=1
voc_datum = {"folder": '',
"source": {"database":"sg vrd visual phrase"},
"filename":k+'.jpg'
}
m['train/%s/w'%k][...]
w, h = int(m['train/%s/w'%k][...]),int(m['train/%s/h'%k][...])
voc_datum['size']={'width':w,'height':h}
objs = []
gt_boxes = m_vp['gt/%s/%s/boxes'%(split_type,k)][...]
gt_labels = m_vp['gt/%s/%s/labels'%(split_type,k)][...]
for i in xrange(gt_boxes.shape[0]):
gt_box = gt_boxes[i]
gt_label = gt_labels[i]
ymin, ymax, xmin, xmax = gt_box[1],gt_box[3],gt_box[0],gt_box[2]
bbox = {'ymin':ymin,'ymax':ymax,'xmin':xmin,'xmax':xmax}
name = zl.idx2name_tri(m_vp,gt_label)
obj = {'name':name,
'bndbox':bbox}
objs.append(obj)
voc_datum['object']=objs
#write to xml
dst_path = os.path.join(anno_root,voc_datum["folder"], voc_datum["filename"][:voc_datum["filename"].rfind('.')]+'.xml')
voc_datum={'annotation':voc_datum}
f = open(dst_path,'w')
f.write(dict2xml(voc_datum)+'\n')
f.close()
print 'images with annotation=%d\n'%cnt
def run_test_visualize():
caffe.set_mode_gpu()
caffe.set_device(0)
m = h5py.File('/home/zawlin/Dropbox/proj/vg1_2_meta.h5', 'r', 'core')
net = caffe.Net(
'models/vg1_2/vgg16/faster_rcnn_end2end/test.prototxt',
'output/models/vg1_2_vgg16_faster_rcnn_finetune_iter_120000.caffemodel',
caffe.TEST)
net2 = caffe.Net(
'models/vg1_2/vgg16/faster_rcnn_end2end/test.prototxt',
'output/models/vg1_2_vgg16_faster_rcnn_finetune_iter_55000.caffemodel',
caffe.TEST)
# net.name = os.path.splitext(os.path.basename(args.caffemodel))[0]
net.name = 'sgvrd'
# if not cfg.TEST.HAS_RPN:
# imdb.set_proposal_method(cfg.TEST.PROPOSAL_METHOD)
"""Test a Fast R-CNN network on an image database."""
# all detections are collected into:
# all_boxes[cls][image] = N x 5 array of detections in
# (x1, y1, x2, y2, score)
root = 'data/vg1_2_2016/Data/test/'
cnt = 0
cv2.namedWindow('im', 0)
cv2.namedWindow('im_single', 0)
images = []
for path, subdirs, files in os.walk(root):
for name in files:
cnt += 1
imid = name.split('.')[0]
fpath = os.path.join(path, name)
images.append(fpath)
random.shuffle(images)
for fpath in images:
imid = fpath.split('/')[-1].replace('.jpg', '')
print imid
imorig = cv2.imread(fpath)
dets1 = detect(imorig, net, 0.01, imid, m)
dets2 = detect(imorig, net2, 0.01, imid, m)
zl.sort_dict_by_key_val(dets1, 'score')
zl.sort_dict_by_key_val(dets2, 'score')
dets1 = dets1[::-1]
dets2 = dets2[::-1]
# print dets1[:4]
# exit(0)
cv2.namedWindow('ctrl')
cv2.destroyWindow('ctrl')
cv2.namedWindow('ctrl')
cv2.createTrackbar('t1', 'ctrl', 200, 1000, nothing)
cv2.createTrackbar('t2', 'ctrl', 200, 1000, nothing)
cv2.createTrackbar('t1idx', 'ctrl', 0, len(dets1) - 1, nothing)
cv2.createTrackbar('t2idx', 'ctrl', 0, len(dets2) - 1, nothing)
while True:
saved_idx = 0
im = imorig.copy()
im_single = imorig.copy()
t1 = cv2.getTrackbarPos('t1', 'ctrl') / 1000.
t2 = cv2.getTrackbarPos('t2', 'ctrl') / 1000.
t1idx = cv2.getTrackbarPos('t1idx', 'ctrl')
t2idx = cv2.getTrackbarPos('t2idx', 'ctrl')
d1 = dets1[t1idx]
cls_name = d1['cls_name'] + '.' + str(t1idx)
di = [d1['x1'], d1['y1'], d1['x2'], d1['y2']]
x, y = int(di[0]), int(di[1])
if x < 10:
x = 15
if y < 10:
y = 15
cv2.putText(im_single, cls_name, (x, y), cv2.FONT_HERSHEY_COMPLEX,
1, (0, 0, 255), 1)
cv2.rectangle(im_single, (di[0], di[1]), (di[2], di[3]),
(255, 0, 0), 2)
d2 = dets2[t2idx]
cls_name = d2['cls_name'] + '.' + str(t2idx)
di = [d2['x1'], d2['y1'], d2['x2'], d2['y2']]
x, y = int(di[0]), int(di[1])
if x < 10:
x = 15
if y < 10:
y = 15
cv2.putText(im_single, cls_name, (x, y), cv2.FONT_HERSHEY_COMPLEX,
1, (0, 0, 255), 1)
cv2.rectangle(im_single, (di[0], di[1]), (di[2], di[3]),
(0, 255, 0), 2)
for i in xrange(len(dets1)):
d = dets1[i]
score = d['score']
if score < t1: continue
cls_name = d['cls_name'] + '.' + str(i)
di = [d['x1'], d['y1'], d['x2'], d['y2']]
x, y = int(di[0]), int(di[1])
if x < 10:
x = 15
if y < 10:
y = 15
cv2.putText(im, cls_name, (x, y), cv2.FONT_HERSHEY_COMPLEX, 1,
(0, 0, 255), 1)
cv2.rectangle(im, (di[0], di[1]), (di[2], di[3]), (255, 0, 0),
2)
#print '%s %f %d %d %d %f\n' % (imid, score, di[0], di[1], di[2], di[3])
for i in xrange(len(dets2)):
d = dets2[i]
score = d['score']
if score < t2: continue
cls_name = d['cls_name'] + '.' + str(i)
di = [d['x1'], d['y1'], d['x2'], d['y2']]
x, y = int(di[0]), int(di[1])
if x < 10:
x = 15
if y < 10:
y = 15
cv2.putText(im, cls_name, (x, y), cv2.FONT_HERSHEY_COMPLEX, 1,
(0, 0, 255), 1)
cv2.rectangle(im, (di[0], di[1]), (di[2], di[3]), (0, 255, 0),
2)
#print '%s %f %d %d %d %f\n' % (imid, score, di[0], di[1], di[2], di[3])
cv2.imshow('im', im)
cv2.imshow('im_single', im_single)
c = cv2.waitKey(100) & 0xFF
if c == ord('s'):
im_folder = 'output/results/examples_obj/' + imid
zl.make_dirs(im_folder)
if not os.path.exists('output/results/examples_obj/' + imid +
'/orig_' + imid + '.jpg'):
cv2.imwrite(
'output/results/examples_obj/' + imid + '/orig_' +
imid + '.jpg', imorig)
cv2.imwrite(
'output/results/examples_obj/' + imid + '/single_' + imid +
'.%d.jpg' % saved_idx, im_single)
saved_idx += 1
elif c == ord(' '):
break
elif c == 27:
exit(0)
def vg_make_voc_format(split_type):
if split_type != 'train' and split_type != 'test':
print 'error'
exit(0)
vg_root = 'data/vg_1.2/'
anno_root = 'data/vg_1.2/voc_format/Annotations/' + split_type + '/'
data_root = 'data/vg_1.2/voc_format/Data/' + split_type + '/'
zl.make_dirs(anno_root + 'VG_100K_2')
zl.make_dirs(anno_root + 'VG_100K')
zl.make_dirs(data_root + 'VG_100K_2')
zl.make_dirs(data_root + 'VG_100K')
client = MongoClient("mongodb://localhost:27017")
db = client.visual_genome_1_2
if split_type == 'train':
db_objs = db.relationships_objects_train.find(no_cursor_timeout=True)
else:
db_objs = db.relationships_objects_test.find(no_cursor_timeout=True)
cnt = 0
zl.tick()
for db_obj in db_objs:
if cnt % 1000 == 0:
print cnt, zl.tock()
zl.tick()
cnt += 1
imid = db_obj['image_id']
im_data = db.image_data.find_one({'image_id': imid})
im_path_full = im_data['url'].replace(
'https://cs.stanford.edu/people/rak248/', '')
im_path_folder = im_path_full.split('/')[0]
im_path_file = im_path_full.split('/')[1]
im_src_path = vg_root + '%s/%s' % (im_path_folder, im_path_file)
im_dst_path = data_root + '%s/%s' % (im_path_folder, im_path_file)
zl.copy_file(im_src_path, im_dst_path)
voc_datum = {
"folder": im_path_folder,
"source": {
"database": "visual genome 1.2"
},
"filename": im_path_file
}
w, h = im_data['width'], im_data['height']
voc_datum['size'] = {'width': w, 'height': h}
objs = []
for o in db_obj['objects']:
ymin, ymax, xmin, xmax = o['y'], o['y'] + o['h'], o[
'x'], o['x'] + o['w']
bbox = {'ymin': ymin, 'ymax': ymax, 'xmin': xmin, 'xmax': xmax}
obj = {'name': o['name'], 'bndbox': bbox}
objs.append(obj)
voc_datum['object'] = objs
#write to xml
dst_path = os.path.join(
anno_root, voc_datum["folder"],
voc_datum["filename"][:voc_datum["filename"].rfind('.')] + '.xml')
voc_datum = {'annotation': voc_datum}
f = open(dst_path, 'w')
f.write(dict2xml(voc_datum) + '\n')
f.close()
print 'images with annotation=%d\n' % cnt
def vg_vphrase_make_voc_format(split_type):
if split_type != 'train' and split_type != 'test':
print 'error'
exit(0)
m = h5py.File('data/vg1_2_meta.h5')
m_vp = h5py.File('data/vg1_2_vp_meta.h5')
vg_root = 'data/vg_1.2/'
root = 'data/vg_1.2/voc_format_vp/'
anno_root = root + 'Annotations/' + split_type + '/'
data_root = root + 'Data/' + split_type + '/'
zl.make_dirs(anno_root + 'VG_100K_2')
zl.make_dirs(anno_root + 'VG_100K')
zl.make_dirs(data_root + 'VG_100K_2')
zl.make_dirs(data_root + 'VG_100K')
client = MongoClient("mongodb://localhost:27017")
db = client.visual_genome_1_2
imdatas = {}
for imdata in db.image_data.find(no_cursor_timeout=True):
imid = str(imdata['image_id'])
imdatas[imid] = imdata
imid2path = {}
for k in m['meta/imid2path'].keys():
imid2path[k] = str(m['meta/imid2path/%s' % k][...])
cnt = 0
zl.tick()
for k in m_vp['gt/%s' % split_type].keys():
if cnt % 1000 == 0:
print cnt, zl.tock()
zl.tick()
cnt += 1
# todo for vg
im_path = imid2path[k]
im_src_path = vg_root + im_path
im_dst_path = data_root + im_path
zl.copy_file(im_src_path, im_dst_path)
voc_datum = {
"folder": im_path.split('/')[0],
"source": {
"database": "sg vrd visual phrase"
},
"filename": im_path.split('/')[1]
}
#todo,remove mongodb from this processing stage
imdata = imdatas[k]
w, h = imdata['width'], imdata['height']
voc_datum['size'] = {'width': w, 'height': h}
objs = []
gt_boxes = m_vp['gt/%s/%s/boxes' % (split_type, k)][...]
gt_labels = m_vp['gt/%s/%s/labels' % (split_type, k)][...]
for i in xrange(gt_boxes.shape[0]):
gt_box = gt_boxes[i]
gt_label = gt_labels[i]
ymin, ymax, xmin, xmax = gt_box[1], gt_box[3], gt_box[0], gt_box[2]
bbox = {'ymin': ymin, 'ymax': ymax, 'xmin': xmin, 'xmax': xmax}
name = zl.idx2name_tri(m_vp, gt_label)
obj = {'name': name, 'bndbox': bbox}
objs.append(obj)
voc_datum['object'] = objs
#write to xml
dst_path = os.path.join(
anno_root, voc_datum["folder"],
voc_datum["filename"][:voc_datum["filename"].rfind('.')] + '.xml')
voc_datum = {'annotation': voc_datum}
f = open(dst_path, 'w')
f.write(dict2xml(voc_datum) + '\n')
f.close()
print 'images with annotation=%d\n' % cnt
def run_retrieval():
h5f = h5py.File('output/vg_results/vg1_2_2016_result_all_100000.all.hdf5')
#h5f = h5py.file('output/results/lu_method_results.hdf5')
data_root = '/home/zawlin/g/py-faster-rcnn/data/vg1_2_2016/Data/test/'
m = h5py.File('/home/zawlin/Dropbox/proj/vg1_2_meta.h5', 'r', 'core')
thresh = 0.0
filters = []
rois = []
images = {}
imids = h5f.keys()
results = {}
cnt = 0
# pre = 'teddy bear_sit on_blanket'
pre = 'cloth_next to_suitcase'
# pre = 'paw_in front of_cat'
# pre = 'racket_hold by_player'
sub_lbl = pre.split('_')[0]
pre_lbl = pre.split('_')[1]
obj_lbl = pre.split('_')[2]
sub_idx = zl.name2idx_cls(m, sub_lbl)
pre_idx = zl.name2idx_pre(m, pre_lbl)
obj_idx = zl.name2idx_cls(m, obj_lbl)
rlp_label = np.array([sub_idx, pre_idx, obj_idx]).astype(np.int16)
results = {}
for imid in imids:
if cnt % 100 == 0:
print cnt, zl.tock()
zl.tick()
cnt += 1
rlp_labels = h5f[imid + '/rlp_labels'][...]
rlp_confs = h5f[imid + '/rlp_confs'][...]
if rlp_confs.shape[0] == 0:
results[imid] = 0.0
continue
zl.tick()
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]
# print confs
# print np.average(confs)
results[imid] = np.average(confs)
results_sorted = zl.sort_dict_by_val(results)
example_folder = 'output/examples_retr_vg/%s/' % pre
zl.make_dirs(example_folder)
cnt = 0
for imid, v in results_sorted[:20]:
sub_boxes = h5f[imid + '/sub_boxes'][...]
obj_boxes = h5f[imid + '/obj_boxes'][...]
rlp_labels = h5f[imid + '/rlp_labels'][...]
rlp_confs = h5f[imid + '/rlp_confs'][...]
indexor = np.arange(rlp_labels.shape[0])
ind = indexor[np.all(rlp_labels == rlp_label, axis=1)]
if ind.shape[0] != 0:
sub_boxes = sub_boxes[ind]
obj_boxes = obj_boxes[ind]
sb = sub_boxes[0]
ob = obj_boxes[0]
im = cv2.imread(data_root + zl.imid2path(m, imid))
cv2.rectangle(im, (sb[0], sb[1]), (sb[2], sb[3]), (0, 200, 0), 1)
cv2.rectangle(im, (ob[0], ob[1]), (ob[2], ob[3]), (0, 0, 200), 1)
cv2.imwrite(example_folder + str(cnt) + '_%s.jpg' % imid, im)
#cv2.imshow('im',im)
cnt += 1
def run_retrieval_vp():
h5f = h5py.File('output/precalc/vg1_2_vp2016_test_new.hdf5')
# print h5f[h5f.keys()[0]].keys()
# exit(0)
#h5f = h5py.file('output/results/lu_method_results.hdf5')
data_root = '/home/zawlin/g/py-faster-rcnn/data/vg1_2_2016/Data/test/'
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')
thresh = 0.0
filters = []
rois = []
images = {}
imids = h5f.keys()
results = {}
cnt = 0
pre = 'teddy bear_sit on_blanket'
# pre = 'paw_in front of_cat'
# pre = 'racket_hold by_player'
r_idx = zl.name2idx_tri(m_vp, pre)
# sub_lbl = pre.split('_')[0]
# pre_lbl = pre.split('_')[1]
# obj_lbl = pre.split('_')[2]
# sub_idx = zl.name2idx_cls(m,sub_lbl)
# pre_idx = zl.name2idx_pre(m,pre_lbl)
# obj_idx = zl.name2idx_cls(m,obj_lbl)
# rlp_label = np.array([sub_idx,pre_idx,obj_idx]).astype(np.int16)
results = {}
for imid in imids:
if cnt % 100 == 0:
print cnt, zl.tock()
zl.tick()
cnt += 1
# rlp_labels = h5f[imid+'/labels'][...]
rlp_confs = h5f[imid + '/confs'][:, r_idx]
ind = np.argsort(rlp_confs)[::-1]
rlp_confs = rlp_confs[ind[:5]]
results[imid] = np.average(rlp_confs)
if rlp_confs.shape[0] == 0:
results[imid] = 0.0
continue
zl.tick()
indexor = np.arange(rlp_labels.shape[0])
# ind = indexor[np.all(rlp_labels==rlp_label,axis=1)]
ind = np.where(rlp_labels == r_idx)[0]
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)
example_folder = 'output/examples_retr_vg_vp/%s/' % pre
zl.make_dirs(example_folder)
cnt = 0
for imid, v in results_sorted[:200]:
boxes = h5f[imid + '/boxes'][...]
rlp_labels = h5f[imid + '/labels'][...]
rlp_confs = h5f[imid + '/confs'][...]
# indexor = np.arange(rlp_labels.shape[0])
# ind = indexor[np.all(rlp_labels==rlp_label,axis=1)]
ind = np.where(rlp_labels == r_idx)[0]
if ind.shape[0] != 0:
boxes = boxes[ind]
sb = boxes[0]
# ob = obj_boxes[0]
im = cv2.imread(data_root + zl.imid2path(m, imid))
cv2.rectangle(im, (sb[0], sb[1]), (sb[2], sb[3]), (0, 200, 0), 1)
# cv2.rectangle(im,(ob[0],ob[1]),(ob[2],ob[3]),(0,0,200),1)
cv2.imwrite(example_folder + str(cnt) + '_%s.jpg' % imid, im)
#cv2.imshow('im',im)
cnt += 1
def run_retrieval_vp_all():
h5f = h5py.File('output/precalc/vg1_2_vp2016_test_new.hdf5', 'r')
# print h5f[h5f.keys()[0]].keys()
# exit(0)
#h5f = h5py.file('output/results/lu_method_results.hdf5')
img_set_file = 'data/vg1_2_2016/ImageSets/test.txt'
imlist = {
line.strip().split(' ')[1]: line.strip().split(' ')[0]
for line in open(img_set_file)
}
data_root = '/home/zawlin/g/py-faster-rcnn/data/vg1_2_2016/Data/test/'
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')
thresh = 0.0
filters = []
rois = []
images = {}
imids = h5f.keys()
results = {}
cnt = 0
# pre = 'teddy bear_sit on_blanket'
pre = 'paw_in front of_cat'
# pre = 'racket_hold by_player'
r_idx = zl.name2idx_tri(m_vp, pre)
# sub_lbl = pre.split('_')[0]
# pre_lbl = pre.split('_')[1]
# obj_lbl = pre.split('_')[2]
# sub_idx = zl.name2idx_cls(m,sub_lbl)
# pre_idx = zl.name2idx_pre(m,pre_lbl)
# obj_idx = zl.name2idx_cls(m,obj_lbl)
# rlp_label = np.array([sub_idx,pre_idx,obj_idx]).astype(np.int16)
results = {}
for imid in imids:
# if cnt>2000:
# break
if cnt % 100 == 0:
print cnt, zl.tock()
zl.tick()
cnt += 1
# rlp_labels = h5f[imid+'/labels'][...]
if imid + '/scores' not in h5f:
print imid
continue
# exit(0)
rlp_confs = h5f[imid + '/scores'][:, r_idx]
# print np.argmax(rlp_confs)
# exit(0)
# ind = np.argsort(rlp_confs)[::-1]
rlp_confs = rlp_confs[np.argmax(rlp_confs)]
# print rlp_confs
results[imid] = np.average(rlp_confs)
# print np.average(rlp_confs)
results_sorted = zl.sort_dict_by_val(results)
example_folder = 'output/examples_retr_vg_vp/%s/' % pre
zl.make_dirs(example_folder)
cnt = 0
for imid, v in results_sorted[:200]:
if imid + '/scores' not in h5f:
continue
#rlp_labels = h5f[imid+'/labels'][...]
impath = imlist[imid]
imid_orig = impath.split('/')[1].replace('.jpg', '')
rlp_confs = h5f[imid + '/scores'][:, r_idx]
ind = np.argsort(rlp_confs)[::-1]
rlp_confs = rlp_confs[ind[:1]]
boxes = h5f[imid + '/boxes'][...][ind, :]
# indexor = np.arange(rlp_labels.shape[0])
# ind = indexor[np.all(rlp_labels==rlp_label,axis=1)]
#boxes = boxes[ind]
sb = boxes[0]
# ob = obj_boxes[0]
im = cv2.imread(data_root + zl.imid2path(m, imid_orig))
cv2.rectangle(im, (sb[0], sb[1]), (sb[2], sb[3]), (0, 200, 0), 1)
# cv2.rectangle(im,(ob[0],ob[1]),(ob[2],ob[3]),(0,0,200),1)
cv2.imwrite(example_folder + str(cnt) + '_%s.jpg' % imid, im)
#cv2.imshow('im',im)
cnt += 1
def run_retrieval_n2():
#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('data/sg_vrd_meta.h5', 'r', 'core')
gt_cache_path = 'output/cache/sg_vrd_gt_cache.pkl'
gt_h5f = {}
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]
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.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
ex_cnt = 0
for i in xrange(len(results_sorted)):
imid, v = results_sorted[i]
if found and ex_cnt >= 100 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)
zl.make_dirs('output/examples_vr_insufficient_gt/' + lbl_str +
'/')
outpath = 'output/examples_vr_insufficient_gt/' + lbl_str + '/' + str(
i) + '.jpg'
if cor: delay = 0
im = cv2.imread(data_root + imid + '.jpg')
if not cor and ex_cnt < 100:
cv2.imwrite(outpath, im)
ex_cnt += 1
if delay == 0:
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(1)&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())
