def __read_file(self, data_dir, dataset):
img_list = list()
mlabel_list = list()
img_dict = dict()
all_img_list = []
with open(self.configer.get('data.{}_label_path'.format(dataset)),
'r') as file_stream:
all_img_list += file_stream.readlines()
if dataset == 'train' and self.configer.get('data.include_val',
default=False):
with open(self.configer.get('data.val_label_path'),
'r') as file_stream:
all_img_list += file_stream.readlines()
for line_cnt in range(len(all_img_list)):
line_items = all_img_list[line_cnt].strip().split()
if len(line_items) == 0:
continue
path = line_items[0]
if not os.path.exists(os.path.join(
data_dir, path)) or not ImageHelper.is_img(path):
Log.warn('Invalid Image Path: {}'.format(
os.path.join(data_dir, path)))
continue
img_list.append(os.path.join(data_dir, path))
mlabel_list.append([int(item) for item in line_items[1:]])
assert len(img_list) > 0
Log.info('Length of {} imgs is {}...'.format(dataset, len(img_list)))
return img_list, mlabel_list
def __init__(self, test_dir=None, aug_transform=None, img_transform=None, configer=None):
super(TestDefaultDataset, self).__init__()
self.configer = configer
self.aug_transform=aug_transform
self.img_transform = img_transform
self.item_list = [(os.path.abspath(os.path.join(test_dir, filename)), filename)
for filename in FileHelper.list_dir(test_dir) if ImageHelper.is_img(filename)]
def __read_list(self, data_dir, list_path):
item_list = []
with open(list_path, 'r') as fr:
for line in fr.readlines():
filename = line.strip().split()[0]
label = None if len(line.strip().split()) == 1 else line.strip().split()[1]
img_path = os.path.join(data_dir, filename)
if not os.path.exists(img_path) or not ImageHelper.is_img(img_path):
Log.error('Image Path: {} is Invalid.'.format(img_path))
exit(1)
item_list.append((img_path, filename, label))
Log.info('There are {} images..'.format(len(item_list)))
return item_list
def __read_file(self, root_dir, dataset, label_path):
img_list = list()
mlabel_list = list()
with open(label_path, 'r') as file_stream:
for line in file_stream.readlines():
line_items = line.rstrip().split()
path = line_items[0]
if not os.path.exists(os.path.join(root_dir, path)) or not ImageHelper.is_img(path):
Log.warn('Invalid Image Path: {}'.format(os.path.join(root_dir, path)))
continue
img_list.append(os.path.join(root_dir, path))
mlabel_list.append([int(item) for item in line_items[1:]])
assert len(img_list) > 0
Log.info('Length of {} imgs is {}...'.format(dataset, len(img_list)))
return img_list, mlabel_list
def __read_and_split_file(self, root_dir, dataset, label_path):
img_list = list()
mlabel_list = list()
select_interval = int(1 / self.configer.get('data', 'val_ratio'))
img_dict = dict()
with open(label_path, 'r') as file_stream:
for line in file_stream.readlines():
label = line.strip().split()[1]
if int(label) in img_dict:
img_dict[int(label)].append(line)
else:
img_dict[int(label)] = [line]
all_img_list = []
for i in sorted(img_dict.keys()):
all_img_list += img_dict[i]
for line_cnt in range(len(all_img_list)):
if line_cnt % select_interval == 0 and dataset == 'train' and not self.configer.get('data', 'include_val'):
continue
if line_cnt % select_interval != 0 and dataset == 'val':
continue
line_items = all_img_list[line_cnt].strip().split()
path = line_items[0]
if not os.path.exists(os.path.join(root_dir, path)) or not ImageHelper.is_img(path):
Log.warn('Invalid Image Path: {}'.format(os.path.join(root_dir, path)))
continue
img_list.append(os.path.join(root_dir, path))
mlabel_list.append([int(item) for item in line_items[1:]])
assert len(img_list) > 0
Log.info('Length of {} imgs is {} after split trainval...'.format(dataset, len(img_list)))
return img_list, mlabel_list