def __init__(self, root, image_sets, preproc=None, target_transform=None,
dataset_name='COCO'):
self.root = root
self.cache_path = os.path.join(self.root, 'cache')
self.image_set = image_sets
self.preproc = preproc
#target_transform = transforms.RandomResizedCrop(300)
self.target_transform = target_transform
self.name = dataset_name
self.ids = list()
self.annotations = list()
self._view_map = {
'minival2014' : 'val2014', # 5k val2014 subset
'valminusminival2014' : 'val2014', # val2014 \setminus minival2014
'test-dev2015' : 'test2015',
}
# self.data_name = list()
# self.data_len = list()
for (year, image_set) in image_sets:
self.image_set = image_set
coco_name = image_set+year
data_name = (self._view_map[coco_name]
if coco_name in self._view_map
else coco_name)
annofile = self._get_ann_file(coco_name)
print('annofile:',annofile)
_COCO = COCO(annofile)
self._COCO = _COCO
self.coco_name = coco_name
cats = _COCO.loadCats(_COCO.getCatIds())
print('cats ', cats)
self._classes = tuple(['__background__'] + [c['name'] for c in cats])
self.num_classes = len(self._classes)
print('class ', self._classes)
self._class_to_ind = dict(zip(self._classes, range(self.num_classes)))
self._class_to_coco_cat_id = dict(zip([c['name'] for c in cats],
_COCO.getCatIds()))
indexes = _COCO.getImgIds()
self.image_indexes = indexes
#print('index ', indexes)
# seems it will reduce the speed during the training.
# self.ids.extend(indexes)
# self.data_len.append(len(indexes))
# self.data_name.append(data_name)
self.ids.extend(self._load_coco_img_path(coco_name, _COCO.getImgFilenames()))
if image_set.find('test') != -1:
print('test set will not load annotations!')
else:
self.annotations.extend(self._load_coco_annotations(coco_name, indexes,_COCO))
def __init__(self,
root,
image_sets,
preproc=None,
target_transform=None,
dataset_name='COCO'):
self.root = None
self.cache_path = os.path.join('/home/zhihuai/yolo', 'cache')
self.image_set = image_sets
self.preproc = preproc
self.target_transform = target_transform
self.name = dataset_name
self.ids = list()
self.annotations = list()
self.OfficeDataset = [
'head_difficult_train',
'head_office_train', # 5k val2014 subset
'head_squatting_train',
'head_steve_train', # val2014 \setminus minival2014
'head_v2_benchmark_0_train'
]
self.CrowdHuman = ['head_CrowdHuman_train']
self.coco_crowdhuman = ['coco_crowdhuman_train']
self.failed_frames = ['failed_frames_train']
self.training_data_resources1 = ['training_data_resources1']
self.training_data_resources2 = ['training_data_resources2']
self.training_data_resources3 = ['training_data_resources3']
self.test_set = ['annotations']
self.num = 0
for image_set in image_sets:
if image_set in self.OfficeDataset:
self.root = os.path.join(root, 'OfficeDataset')
coco_name = image_set
self.data_name = 'OfficeDataset_' #in order to diff some anno has the same name
elif image_set in self.CrowdHuman:
self.root = os.path.join(root, 'CrowdHuman')
coco_name = image_set
self.data_name = 'CrowdHuman_'
elif image_set in self.coco_crowdhuman:
self.root = os.path.join(root, 'tracking_data/training_only',
'coco_crowdhuman')
coco_name = 'annotations'
self.data_name = 'coco_crowdhuman_'
elif image_set in self.failed_frames:
self.root = os.path.join(root, 'tracking_data/training_only',
'failed_frames')
coco_name = 'annotations'
self.data_name = 'failed_frames_'
elif image_set in self.training_data_resources1:
self.root = os.path.join(root, 'tracking_data/training_only',
'training_data_resources1')
coco_name = 'annotations'
self.data_name = 'training_data_resources1_'
elif image_set in self.training_data_resources2:
self.root = os.path.join(root, 'tracking_data/training_only',
'training_data_resources2')
coco_name = 'annotations'
self.data_name = 'training_data_resources2_'
elif image_set in self.training_data_resources3:
self.root = os.path.join(root, 'tracking_data/training_only',
'training_data_resources3')
coco_name = 'annotations'
self.data_name = 'training_data_resources3_'
elif image_set in self.test_set:
self.root = root
coco_name = image_set
self.data_name = 'test_'
annofile = self._get_ann_file(coco_name)
print('annofile', annofile)
_COCO = COCO(annofile)
self._COCO = _COCO
self.coco_name = coco_name
cats = _COCO.loadCats(_COCO.getCatIds())
self._classes = tuple(['__background__'] +
[c['name'] for c in cats])
self.num_classes = len(self._classes)
self._class_to_ind = dict(
zip(self._classes, range(self.num_classes)))
self._class_to_coco_cat_id = dict(
zip([c['name'] for c in cats], _COCO.getCatIds()))
indexes = _COCO.getImgIds()
self.image_indexes = indexes
# seems it will reduce the speed during the training.
# self.ids.extend(indexes)
# self.data_len.append(len(indexes))
# self.data_name.append(data_name)
self.ids.extend(self._load_coco_img_path(coco_name, indexes))
if image_set.find('test') != -1:
print('test set will not load annotations!')
else:
self.annotations.extend(
self._load_coco_annotations(coco_name, indexes, _COCO))
self.num += len(self.image_indexes)
print("image_num", self.num)