def test_list_from_file():
filename = path.join(path.dirname(__file__), 'data/filelist.txt')
filelist = cvb.list_from_file(filename)
assert filelist == ['1.jpg', '2.jpg', '3.jpg', '4.jpg', '5.jpg']
filelist = cvb.list_from_file(filename, prefix='a/')
assert filelist == ['a/1.jpg', 'a/2.jpg', 'a/3.jpg', 'a/4.jpg', 'a/5.jpg']
filelist = cvb.list_from_file(filename, offset=2)
assert filelist == ['3.jpg', '4.jpg', '5.jpg']
filelist = cvb.list_from_file(filename, max_num=2)
assert filelist == ['1.jpg', '2.jpg']
filelist = cvb.list_from_file(filename, offset=3, max_num=3)
assert filelist == ['4.jpg', '5.jpg']
def run(thread_index, thread_num, result, args):
cls_list = ['_' for _ in range(81)]
txt_path = os.path.join(args.base_path, args.img_list)
all_index = cvb.list_from_file(txt_path)
# datasets
num = len(all_index)
thread_result = []
for i in range(num):
if i % thread_num != thread_index:
continue
start_time = time.time()
proposal_base_path = os.path.join(args.base_path, 'score/')
img_index = all_index[i]
image_id = int(img_index)
proposal_path = os.path.join(proposal_base_path, img_index + '.pkl')
if not os.path.exists(proposal_path):
thread_result.append(img_index)
# box_feature, box_box, box_score = pkl.load(open(os.path.join(proposal_path), 'rb'), encoding='iso-8859-1')
# if np.size(box_feature)==0 or np.size(box_box)==0 or np.size(box_score)==0:
# thread_result.append(img_index)
end_time = time.time()
print_time = float(end_time - start_time)
print('thread_index:{}, index:{}, image_id:{}, cost:{}'.format(
thread_index, i, image_id, print_time))
result.extend(thread_result)
def __init__(self, base_path, txt_name):
super(MultiDataset, self).__init__()
self.base_path = base_path
self.txt_path = os.path.join(self.base_path, txt_name)
self.image_index = cvb.list_from_file(self.txt_path)
self.info_path = os.path.join(self.base_path, 'info_1/')
self.gt_path = os.path.join(self.base_path, 'gt/')
self.img_path = os.path.join(self.base_path, 'img/')
self.search_table = self.rank_table()
def run(thread_index, thread_num, result, args):
txt_path = os.path.join(args.base_path, args.img_list)
New2Old = cvb.load(
'/mnt/lustre/liushu1/mask_rcnn/coco-master/PythonAPI/Newlabel.pkl')
proposal_base_path = os.path.join(args.base_path, 'info/')
thread_result = []
val_list = cvb.list_from_file(txt_path)
val_num = len(val_list)
for index, img_name in enumerate(val_list):
if index % thread_num != thread_index:
continue
proposal_path = os.path.join(proposal_base_path, img_name + '.pkl')
# box_feature, box_box, box_score = cvb.load(proposal_path)
box_feature, box_box, box_score = pkl.load(open(
os.path.join(proposal_path), 'rb'),
encoding='iso-8859-1')
box_feature = box_feature.astype(np.float)
box_box = box_box.astype(np.float)
box_score = box_score.astype(np.float)
# bbox = verify_nms(box_box, box_score, img_name, New2Old, iou_thr=0.5, score_thr=0.1)
# bbox = verify_nms_with_box_voting(box_box, box_score, img_name, New2Old, iou_thr=0.5, score_thr=0.01, bv_method='ID')
bbox = verify_soft_nms(box_box,
box_score,
img_name,
New2Old,
iou_thr=0.5,
score_thr=0.01)
# bbox = verify_nms_with_limit(box_box, box_score, img_name, New2Old, iou_thr=0.5)
# cls_num = 0
# for ii in range(1, 81):
# valid_index = np.where(box_score[:,ii]>=0.01)[0]
# valid_num = len(valid_index)
# cls_num += valid_num
thread_result.extend(bbox)
print('img_index:{}, bbox_len:{}'.format(img_name, len(bbox)))
# print('thread_index:{}, index:{}'.format(thread_index, index))
result.extend(thread_result)
(0, 255, 0), 1)
cv2.namedWindow('bb')
cv2.imshow('bb', I)
cv2.waitKey(0)
if __name__ == '__main__':
txt_path = '/mnt/lustre/liushu1/qilu_ex/dataset/test_dev/panet/test.txt'
info_path = '/mnt/lustre/liushu1/qilu_ex/rnn_nms/panet_dcn/testfolder/test16w_new_dev/output/'
save_path = '/mnt/lustre/liushu1/qilu_ex/dataset/test_dev/panet/info/'
if not os.path.exists(save_path):
os.makedirs(save_path)
thread_num = 16
thread_idx = int(sys.argv[1])
img_list = cvb.list_from_file(txt_path)
num_list = len(img_list)
for idx in range(0, num_list):
if idx % thread_num != thread_idx:
continue
start = time.time()
save_pkl_path = os.path.join(save_path, img_list[idx] + '.pkl')
info_txt_path = os.path.join(
info_path, 'COCO_train2014_' + img_list[idx] + '.txt')
if not os.path.exists(info_txt_path):
info_txt_path = os.path.join(
info_path, 'COCO_val2014_' + img_list[idx] + '.txt')
if not os.path.exists(info_txt_path):
info_txt_path = os.path.join(
info_path, 'COCO_test2015_' + img_list[idx] + '.txt')
x2 = x1 + width - 1
y2 = y1 + height - 1
score = ann['score']
cls_index = int(Old2New[str(ann['category_id'])][1])
ann_np[index, :] = x1, y1, x2, y2, score, cls_index
return ann_np
if __name__ == '__main__':
args = parse_args()
New2Old = cvb.load('/data/luqi/coco-master/PythonAPI/Newlabel.pkl')
Old2New = cvb.load('/data/luqi/coco-master/PythonAPI/Oldlabel.pkl')
all_anns = cvb.load(args.output_dir)
anns_dict = make_json_dict(all_anns)
txt_path = os.path.join(args.base_path, args.img_list)
all_index = cvb.list_from_file(txt_path)
results = []
for count, img_index in enumerate(all_index):
gts_info = pkl.load(
open(os.path.join(args.base_path, 'gt/' + img_index + '.pkl'),
'rb'))
gts_box = np.zeros((len(gts_info), 5))
for index, gt in enumerate(gts_info):
gts_box[index, :] = gt['bbox']
# if gts_box[index, 4]>=100:
# gts_box[index, 4] -= 100
unique_gts = np.unique(gts_box[:, 4]).astype(np.int16)
key = int(img_index)
ann_dict = anns_dict[key]
ann_matrix = trans_np(ann_dict, Old2New)
