def generate_samples(self, curr_bbox, positive, init=False):
if init:
if positive:
n = self.opts['nPos_init']
Thre = self.opts['posThre_init']
else:
n = self.opts['nNeg_init']
Thre = self.opts['negThre_init']
else:
if positive:
n = self.opts['nPos_online']
Thre = self.opts['posThre_online']
else:
n = self.opts['nNeg_online']
Thre = self.opts['negThre_online']
assert n > 0, "if n = 0, don't initialize this class"
if positive:
examples = gen_samples('gaussian', curr_bbox, n * 2, self.opts,
self.opts['finetune_trans'],
self.opts['finetune_scale_factor'])
r = overlap_ratio(examples,
np.matlib.repmat(curr_bbox, len(examples), 1))
examples = examples[np.array(r) > Thre]
examples = examples[np.random.randint(
low=0, high=len(examples), size=min(len(examples), n)), :]
action_labels = gen_action_labels(self.opts['num_actions'],
self.opts, np.array(examples),
curr_bbox)
# score labels: 1 is positive. 0 is negative
score_labels = list(np.ones(len(examples), dtype=int))
else:
examples = gen_samples('uniform', curr_bbox, n * 2, self.opts, 2,
5)
r = overlap_ratio(examples,
np.matlib.repmat(curr_bbox, len(examples), 1))
examples = examples[np.array(r) < Thre]
examples = examples[np.random.randint(
low=0, high=len(examples), size=min(len(examples), n)), :]
action_labels = np.full((self.opts['num_actions'], len(examples)),
fill_value=-1)
# score labels: 1 is positive. 0 is negative
score_labels = list(np.zeros(len(examples), dtype=int))
action_labels = np.transpose(action_labels).tolist()
bboxes = examples
labels = action_labels
return bboxes, labels, score_labels
def process_data_vot(train_sequences, vid_info, opt, train_db_pos,
train_db_neg, lock):
opts = opt.copy()
train_db_pos_gpu = []
train_db_neg_gpu = []
for train_i in range(len(train_sequences)):
train_db_pos_ = {
'img_path': [],
'bboxes': [],
'labels': [],
'score_labels': []
}
train_db_neg_ = {
'img_path': [],
'bboxes': [],
'labels': [],
'score_labels': []
}
img_idx = train_sequences[train_i]
gt_bbox = vid_info['gt'][img_idx]
if len(gt_bbox) == 0:
continue
pos_examples = []
while len(pos_examples) < opts['nPos_train']:
pos = gen_samples('gaussian', gt_bbox, opts['nPos_train'] * 5,
opts, 0.1, 5)
r = overlap_ratio(pos, np.matlib.repmat(gt_bbox, len(pos), 1))
pos = pos[np.array(r) > opts['posThre_train']]
if len(pos) == 0:
continue
pos = pos[np.random.
randint(low=0,
high=len(pos),
size=min(len(pos), opts['nPos_train'] -
len(pos_examples))), :]
pos_examples.extend(pos)
neg_examples = []
while len(neg_examples) < opts['nNeg_train']:
# in original code, this 1 line below use opts['nPos_train'] instead of opts['nNeg_train']
neg = gen_samples('gaussian', gt_bbox, opts['nNeg_train'] * 5,
opts, 2, 10)
r = overlap_ratio(neg, np.matlib.repmat(gt_bbox, len(neg), 1))
neg = neg[np.array(r) < opts['negThre_train']]
if len(neg) == 0:
continue
neg = neg[np.random.
randint(low=0,
high=len(neg),
size=min(len(neg), opts['nNeg_train'] -
len(neg_examples))), :]
neg_examples.extend(neg)
# examples = pos_examples + neg_examples
action_labels_pos = gen_action_labels(opts['num_actions'], opts,
np.array(pos_examples), gt_bbox)
action_labels_neg = np.full((opts['num_actions'], len(neg_examples)),
fill_value=-1)
action_labels_pos = np.transpose(action_labels_pos).tolist()
action_labels_neg = np.transpose(action_labels_neg).tolist()
# action_labels = action_labels_pos + action_labels_neg
train_db_pos_['img_path'] = np.full(len(pos_examples),
vid_info['img_files'][img_idx])
train_db_pos_['bboxes'] = pos_examples
train_db_pos_['labels'] = action_labels_pos
# score labels: 1 is positive. 0 is negative
train_db_pos_['score_labels'] = list(
np.ones(len(pos_examples), dtype=int))
train_db_neg_['img_path'] = np.full(len(neg_examples),
vid_info['img_files'][img_idx])
train_db_neg_['bboxes'] = neg_examples
train_db_neg_['labels'] = action_labels_neg
# score labels: 1 is positive. 0 is negative
train_db_neg_['score_labels'] = list(
np.zeros(len(neg_examples), dtype=int))
train_db_pos_gpu.append(train_db_pos_)
train_db_neg_gpu.append(train_db_neg_)
try:
lock.acquire()
#print("len(train_db_pos_gpu): %d"%len(train_db_pos_gpu))
train_db_pos.extend(train_db_pos_gpu)
#print("len(train_db_pos): %d" % len(train_db_pos))
#print("len(train_db_neg_gpu): %d" % len(train_db_neg_gpu))
train_db_neg.extend(train_db_neg_gpu)
#print("len(train_db_neg): %d" % len(train_db_neg))
except Exception as err:
raise err
finally:
lock.release()
def process_data_ILSVR(img_paths, opt, train_db_pos_neg_all, lock):
opts = opt.copy()
train_db_pos_neg_gpu = []
# train_db_neg_gpu = []
for train_i in img_paths:
train_db_pos_ = {
'img_path': '',
'bboxes': [],
'labels': [],
'score_labels': []
}
train_db_neg_ = {
'img_path': '',
'bboxes': [],
'labels': [],
'score_labels': []
}
#img_idx = train_sequences[train_i]
#gt_bbox = vid_info['gt'][img_idx]
#if len(gt_bbox) == 0:
# continue
gt_file_path = '../datasets/data/ILSVRC/Annotations/VID/train/' + train_i + '.xml'
#gt_bbox=get_xml_box_label(gt_file_path)
#opts['imgSize'] = get_xml_img_size(gt_file_path)
imginfo = get_xml_img_info(gt_file_path)
gt_bboxs = imginfo['gts']
opts['imgSize'] = imginfo['imgsize']
img_path = '../datasets/data/ILSVRC/Data/VID/train/' + train_i + '.JPEG'
for gt_bbox in gt_bboxs:
train_db_pos_neg = {
'img_path': '',
'bboxes': [],
'labels': [],
'score_labels': []
}
pos_examples = []
while len(pos_examples) < opts['nPos_train']:
pos = gen_samples('gaussian', gt_bbox, opts['nPos_train'] * 5,
opts, 0.1, 5)
r = overlap_ratio(pos, np.matlib.repmat(gt_bbox, len(pos), 1))
pos = pos[np.array(r) > opts['posThre_train']]
if len(pos) == 0:
#continue
break
pos = pos[np.random.randint(low=0,
high=len(pos),
size=min(
len(pos), opts['nPos_train'] -
len(pos_examples))), :]
pos_examples.extend(pos)
neg_examples = []
while len(neg_examples) < opts['nNeg_train']:
# in original code, this 1 line below use opts['nPos_train'] instead of opts['nNeg_train']
neg = gen_samples('gaussian', gt_bbox, opts['nNeg_train'] * 5,
opts, 2, 10)
r = overlap_ratio(neg, np.matlib.repmat(gt_bbox, len(neg), 1))
neg = neg[np.array(r) < opts['negThre_train']]
if len(neg) == 0:
#continue
break
neg = neg[np.random.randint(low=0,
high=len(neg),
size=min(
len(neg), opts['nNeg_train'] -
len(neg_examples))), :]
neg_examples.extend(neg)
# examples = pos_examples + neg_examples
action_labels_pos = gen_action_labels(opts['num_actions'], opts,
np.array(pos_examples),
gt_bbox)
action_labels_neg = np.full(
(opts['num_actions'], len(neg_examples)), fill_value=-1)
action_labels_pos = np.transpose(action_labels_pos).tolist()
action_labels_neg = np.transpose(action_labels_neg).tolist()
# action_labels = action_labels_pos + action_labels_neg
# train_db_pos_['bboxes'].extend(pos_examples)
# train_db_pos_['labels'].extend(action_labels_pos)
# # score labels: 1 is positive. 0 is negative
# train_db_pos_['score_labels'].extend(list(np.ones(len(pos_examples), dtype=int)))
#
#
# train_db_neg_['bboxes'].extend(neg_examples)
# train_db_neg_['labels'].extend(action_labels_neg)
# # score labels: 1 is positive. 0 is negative
# train_db_neg_['score_labels'].extend(list(np.zeros(len(neg_examples), dtype=int)))
train_db_pos_neg['bboxes'].extend(pos_examples)
train_db_pos_neg['labels'].extend(action_labels_pos)
# score labels: 1 is positive. 0 is negative
train_db_pos_neg['score_labels'].extend(
list(np.ones(len(pos_examples), dtype=int)))
train_db_pos_neg['bboxes'].extend(neg_examples)
train_db_pos_neg['labels'].extend(action_labels_neg)
# score labels: 1 is positive. 0 is negative
train_db_pos_neg['score_labels'].extend(
list(np.zeros(len(neg_examples), dtype=int)))
train_db_pos_neg['img_path'] = img_path
# train_db_pos_['img_path'] = img_path
# train_db_neg_['img_path'] = img_path
# if len(train_db_pos_['bboxes']) != 0 and len(train_db_neg_['bboxes']) != 0:
# train_db_pos_gpu.append(train_db_pos_)
# train_db_neg_gpu.append(train_db_neg_)
if len(train_db_pos_neg['bboxes']) == (opts['nPos_train'] +
opts['nNeg_train']):
train_db_pos_neg_gpu.append(train_db_pos_neg)
# train_db_neg_gpu.append(train_db_neg_)
# box_ii += 1
# img_ii += 1
# if img_ii==3471:
# print("when gt_skip set to 200, and the img_ii=3472, the gen_samples function can't produce examples that iou>thred")
# #'ILSVRC2015_VID_train_0002/ILSVRC2015_train_00633000/000025'
#reason:the img is so small and unclear
# if img_ii%1000==0 and img_ii!=0:
# t9=time.time()
# real_time=t9-t2
# all_time=t9-t0
# all_h=all_time//3600
# all_m=all_time%3600//60
# all_s=all_time%60
# speed_img=1000/real_time
# speed_box=(box_ii-box_ii_start)/real_time
# all_speed_img=img_ii/all_time
# all_speed_box = box_ii/all_time
# print('\ndone imgs: %d , done boxes: %d , all imgs: %d. '%(img_ii,box_ii,all_img_num))
# print('real_time speed: %d imgs/s, %d boxes/s'%(speed_img,speed_box))
# print('avg_time speed: %d imgs/s, %d boxes/s' % (all_speed_img, all_speed_box))
# print('spend time: %d h %d m %d s (%d s)'%(all_h,all_m,all_s,all_time))
# box_ii_start=box_ii
# t2=time.time()
try:
lock.acquire()
# print("len(train_db_pos_gpu): %d" % len(train_db_pos_gpu))
train_db_pos_neg_all.extend(train_db_pos_neg_gpu)
# print("len(train_db_pos): %d" % len(train_db_pos))
# print("len(train_db_neg_gpu): %d" % len(train_db_neg_gpu))
# train_db_neg.extend(train_db_neg_gpu)
# print("len(train_db_neg): %d" % len(train_db_neg))
except Exception as err:
raise err
finally:
lock.release()
def get_train_dbs(vid_info, opts):
img = cv2.imread(vid_info['img_files'][0])
opts['scale_factor'] = 1.05
opts['imgSize'] = list(img.shape)
gt_skip = opts['train']['gt_skip']
if vid_info['db_name'] == 'alov300':
train_sequences = vid_info['gt_use'] == 1
else:
train_sequences = list(range(0, vid_info['nframes'], gt_skip))
train_db_pos = []
train_db_neg = []
for train_i in range(len(train_sequences)):
train_db_pos_ = {
'img_path': [],
'bboxes': [],
'labels': [],
'score_labels': []
}
train_db_neg_ = {
'img_path': [],
'bboxes': [],
'labels': [],
'score_labels': []
}
img_idx = train_sequences[train_i]
gt_bbox = vid_info['gt'][img_idx]
if len(gt_bbox) == 0:
continue
pos_examples = []
while len(pos_examples) < opts['nPos_train']:
pos = gen_samples('gaussian', gt_bbox, opts['nPos_train'] * 5,
opts, 0.1, 5)
r = overlap_ratio(pos, np.matlib.repmat(gt_bbox, len(pos), 1))
pos = pos[np.array(r) > opts['posThre_train']]
if len(pos) == 0:
continue
pos = pos[np.random.
randint(low=0,
high=len(pos),
size=min(len(pos), opts['nPos_train'] -
len(pos_examples))), :]
pos_examples.extend(pos)
neg_examples = []
while len(neg_examples) < opts['nNeg_train']:
# in original code, this 1 line below use opts['nPos_train'] instead of opts['nNeg_train']
neg = gen_samples('gaussian', gt_bbox, opts['nNeg_train'] * 5,
opts, 2, 10)
r = overlap_ratio(neg, np.matlib.repmat(gt_bbox, len(neg), 1))
neg = neg[np.array(r) < opts['negThre_train']]
if len(neg) == 0:
continue
neg = neg[np.random.
randint(low=0,
high=len(neg),
size=min(len(neg), opts['nNeg_train'] -
len(neg_examples))), :]
neg_examples.extend(neg)
show_examples_test(pos_examples, neg_examples,
vid_info['img_files'][img_idx])
# examples = pos_examples + neg_examples
action_labels_pos = gen_action_labels(opts['num_actions'], opts,
np.array(pos_examples), gt_bbox)
action_labels_neg = np.full((opts['num_actions'], len(neg_examples)),
fill_value=-1)
action_labels_pos = np.transpose(action_labels_pos).tolist()
action_labels_neg = np.transpose(action_labels_neg).tolist()
# action_labels = action_labels_pos + action_labels_neg
train_db_pos_['img_path'] = np.full(len(pos_examples),
vid_info['img_files'][img_idx])
train_db_pos_['bboxes'] = pos_examples
train_db_pos_['labels'] = action_labels_pos
# score labels: 1 is positive. 0 is negative
train_db_pos_['score_labels'] = list(
np.ones(len(pos_examples), dtype=int))
train_db_neg_['img_path'] = np.full(len(neg_examples),
vid_info['img_files'][img_idx])
train_db_neg_['bboxes'] = neg_examples
train_db_neg_['labels'] = action_labels_neg
# score labels: 1 is positive. 0 is negative
train_db_neg_['score_labels'] = list(
np.zeros(len(neg_examples), dtype=int))
train_db_pos.append(train_db_pos_)
train_db_neg.append(train_db_neg_)
return train_db_pos, train_db_neg