def __init__(self, root='data', split_id=0, verbose=True, **kwargs):
super(GRID, self).__init__()
self.dataset_dir = osp.join(root, self.dataset_dir)
self.dataset_url = 'http://personal.ie.cuhk.edu.hk/~ccloy/files/datasets/underground_reid.zip'
self.probe_path = osp.join(self.dataset_dir, 'underground_reid', 'probe')
self.gallery_path = osp.join(self.dataset_dir, 'underground_reid', 'gallery')
self.split_mat_path = osp.join(self.dataset_dir, 'underground_reid', 'features_and_partitions.mat')
self.split_path = osp.join(self.dataset_dir, 'splits.json')
self._download_data()
self._check_before_run()
self._prepare_split()
splits = read_json(self.split_path)
if split_id >= len(splits):
raise ValueError("split_id exceeds range, received {}, but expected between 0 and {}".format(split_id, len(splits)-1))
split = splits[split_id]
train = split['train']
query = split['query']
gallery = split['gallery']
train = [tuple(item) for item in train]
query = [tuple(item) for item in query]
gallery = [tuple(item) for item in gallery]
num_train_pids = split['num_train_pids']
num_query_pids = split['num_query_pids']
num_gallery_pids = split['num_gallery_pids']
num_train_imgs = len(train)
num_query_imgs = len(query)
num_gallery_imgs = len(gallery)
num_total_pids = num_train_pids + num_gallery_pids
num_total_imgs = num_train_imgs + num_query_imgs + num_gallery_imgs
if verbose:
print("=> GRID loaded")
print("Dataset statistics:")
print(" ------------------------------")
print(" subset | # ids | # images")
print(" ------------------------------")
print(" train | {:5d} | {:8d}".format(num_train_pids, num_train_imgs))
print(" query | {:5d} | {:8d}".format(num_query_pids, num_query_imgs))
print(" gallery | {:5d} | {:8d}".format(num_gallery_pids, num_gallery_imgs))
print(" ------------------------------")
print(" total | {:5d} | {:8d}".format(num_total_pids, num_total_imgs))
print(" ------------------------------")
self.train = train
self.query = query
self.gallery = gallery
self.num_train_pids = num_train_pids
self.num_query_pids = num_query_pids
self.num_gallery_pids = num_gallery_pids
def __init__(self, root='data', split_id=0, verbose=True, **kwargs):
super(VIPeR, self).__init__()
self.dataset_dir = osp.join(root, self.dataset_dir)
self.dataset_url = 'http://users.soe.ucsc.edu/~manduchi/VIPeR.v1.0.zip'
self.cam_a_path = osp.join(self.dataset_dir, 'VIPeR', 'cam_a')
self.cam_b_path = osp.join(self.dataset_dir, 'VIPeR', 'cam_b')
self.split_path = osp.join(self.dataset_dir, 'splits.json')
self._download_data()
self._check_before_run()
self._prepare_split()
splits = read_json(self.split_path)
if split_id >= len(splits):
raise ValueError("split_id exceeds range, received {}, but expected between 0 and {}".format(split_id, len(splits)-1))
split = splits[split_id]
train = split['train']
query = split['query'] # query and gallery share the same images
gallery = split['gallery']
train = [tuple(item) for item in train]
query = [tuple(item) for item in query]
gallery = [tuple(item) for item in gallery]
num_train_pids = split['num_train_pids']
num_query_pids = split['num_query_pids']
num_gallery_pids = split['num_gallery_pids']
num_train_imgs = len(train)
num_query_imgs = len(query)
num_gallery_imgs = len(gallery)
num_total_pids = num_train_pids + num_query_pids
num_total_imgs = num_train_imgs + num_query_imgs
if verbose:
print("=> VIPeR loaded")
print("Dataset statistics:")
print(" ------------------------------")
print(" subset | # ids | # images")
print(" ------------------------------")
print(" train | {:5d} | {:8d}".format(num_train_pids, num_train_imgs))
print(" query | {:5d} | {:8d}".format(num_query_pids, num_query_imgs))
print(" gallery | {:5d} | {:8d}".format(num_gallery_pids, num_gallery_imgs))
print(" ------------------------------")
print(" total | {:5d} | {:8d}".format(num_total_pids, num_total_imgs))
print(" ------------------------------")
self.train = train
self.query = query
self.gallery = gallery
self.num_train_pids = num_train_pids
self.num_query_pids = num_query_pids
self.num_gallery_pids = num_gallery_pids
def __init__(self, root='data', split_id=0, min_seq_len=0, verbose=True, **kwargs):
self.dataset_dir = osp.join(root, self.dataset_dir)
self.split_path = osp.join(self.dataset_dir, 'splits_prid2011.json')
self.cam_a_path = osp.join(self.dataset_dir, 'prid_2011', 'multi_shot', 'cam_a')
self.cam_b_path = osp.join(self.dataset_dir, 'prid_2011', 'multi_shot', 'cam_b')
self._check_before_run()
splits = read_json(self.split_path)
if split_id >= len(splits):
raise ValueError("split_id exceeds range, received {}, but expected between 0 and {}".format(split_id, len(splits)-1))
split = splits[split_id]
train_dirs, test_dirs = split['train'], split['test']
print("# train identites: {}, # test identites {}".format(len(train_dirs), len(test_dirs)))
train, num_train_tracklets, num_train_pids, num_imgs_train = \
self._process_data(train_dirs, cam1=True, cam2=True)
query, num_query_tracklets, num_query_pids, num_imgs_query = \
self._process_data(test_dirs, cam1=True, cam2=False)
gallery, num_gallery_tracklets, num_gallery_pids, num_imgs_gallery = \
self._process_data(test_dirs, cam1=False, cam2=True)
num_imgs_per_tracklet = num_imgs_train + num_imgs_query + num_imgs_gallery
min_num = np.min(num_imgs_per_tracklet)
max_num = np.max(num_imgs_per_tracklet)
avg_num = np.mean(num_imgs_per_tracklet)
num_total_pids = num_train_pids + num_query_pids
num_total_tracklets = num_train_tracklets + num_query_tracklets + num_gallery_tracklets
if verbose:
print("=> PRID2011 loaded")
print("Dataset statistics:")
print(" ------------------------------")
print(" subset | # ids | # tracklets")
print(" ------------------------------")
print(" train | {:5d} | {:8d}".format(num_train_pids, num_train_tracklets))
print(" query | {:5d} | {:8d}".format(num_query_pids, num_query_tracklets))
print(" gallery | {:5d} | {:8d}".format(num_gallery_pids, num_gallery_tracklets))
print(" ------------------------------")
print(" total | {:5d} | {:8d}".format(num_total_pids, num_total_tracklets))
print(" number of images per tracklet: {} ~ {}, average {:.1f}".format(min_num, max_num, avg_num))
print(" ------------------------------")
self.train = train
self.query = query
self.gallery = gallery
self.num_train_pids = num_train_pids
self.num_query_pids = num_query_pids
self.num_gallery_pids = num_gallery_pids
def __init__(self, root='data', split_id=0, verbose=True, **kwargs):
super(iLIDS, self).__init__()
self.dataset_dir = osp.join(root, self.dataset_dir)
self.dataset_url = 'http://www.eecs.qmul.ac.uk/~xiatian/iLIDS-VID/iLIDS-VID.tar'
self.data_dir = osp.join(self.dataset_dir, 'i-LIDS-VID')
self.split_dir = osp.join(self.dataset_dir, 'train-test people splits')
self.split_mat_path = osp.join(self.split_dir, 'train_test_splits_ilidsvid.mat')
self.split_path = osp.join(self.dataset_dir, 'splits.json')
self.cam_1_path = osp.join(self.dataset_dir, 'i-LIDS-VID/images/cam1') # differ from video
self.cam_2_path = osp.join(self.dataset_dir, 'i-LIDS-VID/images/cam2')
self._download_data()
self._check_before_run()
self._prepare_split()
splits = read_json(self.split_path)
if split_id >= len(splits):
raise ValueError("split_id exceeds range, received {}, but expected between 0 and {}".format(split_id, len(splits)-1))
split = splits[split_id]
train_dirs, test_dirs = split['train'], split['test']
print("# train identites: {}, # test identites {}".format(len(train_dirs), len(test_dirs)))
train, num_train_imgs, num_train_pids = self._process_data(train_dirs, cam1=True, cam2=True)
query, num_query_imgs, num_query_pids = self._process_data(test_dirs, cam1=True, cam2=False)
gallery, num_gallery_imgs, num_gallery_pids = self._process_data(test_dirs, cam1=False, cam2=True)
num_total_pids = num_train_pids + num_query_pids
num_total_imgs = num_train_imgs + num_query_imgs
if verbose:
print("=> iLIDS (single-shot) loaded")
print("Dataset statistics:")
print(" ------------------------------")
print(" subset | # ids | # images")
print(" ------------------------------")
print(" train | {:5d} | {:8d}".format(num_train_pids, num_train_imgs))
print(" query | {:5d} | {:8d}".format(num_query_pids, num_query_imgs))
print(" gallery | {:5d} | {:8d}".format(num_gallery_pids, num_gallery_imgs))
print(" ------------------------------")
print(" total | {:5d} | {:8d}".format(num_total_pids, num_total_imgs))
print(" ------------------------------")
self.train = train
self.query = query
self.gallery = gallery
self.num_train_pids = num_train_pids
self.num_query_pids = num_query_pids
self.num_gallery_pids = num_gallery_pids
def _process_dir(self, dir_path, json_path, relabel):
if osp.exists(json_path):
print("=> {} generated before, awesome!".format(json_path))
split = read_json(json_path)
return split['tracklets'], split['num_tracklets'], split[
'num_pids'], split['num_imgs_per_tracklet']
print(
"=> Automatically generating split (might take a while for the first time, have a coffe)"
)
pdirs = glob.glob(osp.join(dir_path, '*')) # avoid .DS_Store
print("Processing {} with {} person identities".format(
dir_path, len(pdirs)))
pid_container = set()
for pdir in pdirs:
pid = int(osp.basename(pdir))
pid_container.add(pid)
pid2label = {pid: label for label, pid in enumerate(pid_container)}
tracklets = []
num_imgs_per_tracklet = []
for pdir in pdirs:
pid = int(osp.basename(pdir))
if relabel: pid = pid2label[pid]
tdirs = glob.glob(osp.join(pdir, '*'))
for tdir in tdirs:
raw_img_paths = glob.glob(osp.join(tdir, '*.jpg'))
num_imgs = len(raw_img_paths)
if num_imgs < self.min_seq_len:
continue
num_imgs_per_tracklet.append(num_imgs)
img_paths = []
for img_idx in range(num_imgs):
# some tracklet starts from 0002 instead of 0001
img_idx_name = 'F' + str(img_idx + 1).zfill(4)
res = glob.glob(
osp.join(tdir, '*' + img_idx_name + '*.jpg'))
if len(res) == 0:
print(
"Warn: index name {} in {} is missing, jump to next"
.format(img_idx_name, tdir))
continue
img_paths.append(res[0])
img_name = osp.basename(img_paths[0])
if img_name.find('_') == -1:
# old naming format: 0001C6F0099X30823.jpg
camid = int(img_name[5]) - 1
else:
# new naming format: 0001_C6_F0099_X30823.jpg
camid = int(img_name[6]) - 1
img_paths = tuple(img_paths)
tracklets.append((img_paths, pid, camid))
num_pids = len(pid_container)
num_tracklets = len(tracklets)
print("Saving split to {}".format(json_path))
split_dict = {
'tracklets': tracklets,
'num_tracklets': num_tracklets,
'num_pids': num_pids,
'num_imgs_per_tracklet': num_imgs_per_tracklet,
}
write_json(split_dict, json_path)
return tracklets, num_tracklets, num_pids, num_imgs_per_tracklet
def __init__(self, root='data', split_id=0, verbose=True, **kwargs):
self.dataset_dir = osp.join(root, self.dataset_dir)
self.dataset_url = 'http://www.eecs.qmul.ac.uk/~xiatian/iLIDS-VID/iLIDS-VID.tar'
self.data_dir = osp.join(self.dataset_dir, 'i-LIDS-VID')
self.split_dir = osp.join(self.dataset_dir, 'train-test people splits')
self.split_mat_path = osp.join(self.split_dir,
'train_test_splits_ilidsvid.mat')
self.split_path = osp.join(self.dataset_dir, 'splits.json')
self.cam_1_path = osp.join(self.dataset_dir,
'i-LIDS-VID/sequences/cam1')
self.cam_2_path = osp.join(self.dataset_dir,
'i-LIDS-VID/sequences/cam2')
self._download_data()
self._check_before_run()
self._prepare_split()
splits = read_json(self.split_path)
if split_id >= len(splits):
raise ValueError(
"split_id exceeds range, received {}, but expected between 0 and {}"
.format(split_id,
len(splits) - 1))
split = splits[split_id]
train_dirs, test_dirs = split['train'], split['test']
print("# train identites: {}, # test identites {}".format(
len(train_dirs), len(test_dirs)))
train, num_train_tracklets, num_train_pids, num_imgs_train = \
self._process_data(train_dirs, cam1=True, cam2=True)
query, num_query_tracklets, num_query_pids, num_imgs_query = \
self._process_data(test_dirs, cam1=True, cam2=False)
gallery, num_gallery_tracklets, num_gallery_pids, num_imgs_gallery = \
self._process_data(test_dirs, cam1=False, cam2=True)
num_imgs_per_tracklet = num_imgs_train + num_imgs_query + num_imgs_gallery
min_num = np.min(num_imgs_per_tracklet)
max_num = np.max(num_imgs_per_tracklet)
avg_num = np.mean(num_imgs_per_tracklet)
num_total_pids = num_train_pids + num_query_pids
num_total_tracklets = num_train_tracklets + num_query_tracklets + num_gallery_tracklets
if verbose:
print("=> iLIDS-VID loaded")
print("Dataset statistics:")
print(" ------------------------------")
print(" subset | # ids | # tracklets")
print(" ------------------------------")
print(" train | {:5d} | {:8d}".format(num_train_pids,
num_train_tracklets))
print(" query | {:5d} | {:8d}".format(num_query_pids,
num_query_tracklets))
print(" gallery | {:5d} | {:8d}".format(num_gallery_pids,
num_gallery_tracklets))
print(" ------------------------------")
print(" total | {:5d} | {:8d}".format(num_total_pids,
num_total_tracklets))
print(" number of images per tracklet: {} ~ {}, average {:.1f}".
format(min_num, max_num, avg_num))
print(" ------------------------------")
self.train = train
self.query = query
self.gallery = gallery
self.num_train_pids = num_train_pids
self.num_query_pids = num_query_pids
self.num_gallery_pids = num_gallery_pids
def __init__(self, root='data', split_id=0, verbose=True, **kwargs):
super(CUHK01, self).__init__()
self.dataset_dir = osp.join(root, self.dataset_dir)
self.zip_path = osp.join(self.dataset_dir, 'CUHK01.zip')
self.campus_dir = osp.join(self.dataset_dir, 'campus')
self.split_path = osp.join(self.dataset_dir, 'splits.json')
self._extract_file()
self._check_before_run()
self._prepare_split()
splits = read_json(self.split_path)
if split_id >= len(splits):
raise ValueError(
"split_id exceeds range, received {}, but expected between 0 and {}"
.format(split_id,
len(splits) - 1))
split = splits[split_id]
train = split['train']
query = split['query']
gallery = split['gallery']
train = [tuple(item) for item in train]
query = [tuple(item) for item in query]
gallery = [tuple(item) for item in gallery]
num_train_pids = split['num_train_pids']
num_query_pids = split['num_query_pids']
num_gallery_pids = split['num_gallery_pids']
num_train_imgs = len(train)
num_query_imgs = len(query)
num_gallery_imgs = len(gallery)
num_total_pids = num_train_pids + num_query_pids
num_total_imgs = num_train_imgs + num_query_imgs
if verbose:
print("=> CUHK01 loaded")
print("Dataset statistics:")
print(" ------------------------------")
print(" subset | # ids | # images")
print(" ------------------------------")
print(" train | {:5d} | {:8d}".format(num_train_pids,
num_train_imgs))
print(" query | {:5d} | {:8d}".format(num_query_pids,
num_query_imgs))
print(" gallery | {:5d} | {:8d}".format(num_gallery_pids,
num_gallery_imgs))
print(" ------------------------------")
print(" total | {:5d} | {:8d}".format(num_total_pids,
num_total_imgs))
print(" ------------------------------")
self.train = train
self.query = query
self.gallery = gallery
self.num_train_pids = num_train_pids
self.num_query_pids = num_query_pids
self.num_gallery_pids = num_gallery_pids
def __init__(self,
root='data',
split_id=0,
min_seq_len=0,
verbose=True,
**kwargs):
super(PRID450S, self).__init__()
self.dataset_dir = osp.join(root, self.dataset_dir)
self.dataset_url = 'https://files.icg.tugraz.at/f/8c709245bb/?raw=1'
self.split_path = osp.join(self.dataset_dir, 'splits.json')
self.cam_a_path = osp.join(self.dataset_dir, 'cam_a')
self.cam_b_path = osp.join(self.dataset_dir, 'cam_b')
self._download_data()
self._check_before_run()
self._prepare_split()
splits = read_json(self.split_path)
if split_id >= len(splits):
raise ValueError(
"split_id exceeds range, received {}, but expected between 0 and {}"
.format(split_id,
len(splits) - 1))
split = splits[split_id]
train = split['train']
query = split['query']
gallery = split['gallery']
train = [tuple(item) for item in train]
query = [tuple(item) for item in query]
gallery = [tuple(item) for item in gallery]
num_train_pids = split['num_train_pids']
num_query_pids = split['num_query_pids']
num_gallery_pids = split['num_gallery_pids']
num_train_imgs = len(train)
num_query_imgs = len(query)
num_gallery_imgs = len(gallery)
num_total_pids = num_train_pids + num_query_pids
num_total_imgs = num_train_imgs + num_query_imgs
if verbose:
print("=> PRID450S loaded")
print("Dataset statistics:")
print(" ------------------------------")
print(" subset | # ids | # images")
print(" ------------------------------")
print(" train | {:5d} | {:8d}".format(num_train_pids,
num_train_imgs))
print(" query | {:5d} | {:8d}".format(num_query_pids,
num_query_imgs))
print(" gallery | {:5d} | {:8d}".format(num_gallery_pids,
num_gallery_imgs))
print(" ------------------------------")
print(" total | {:5d} | {:8d}".format(num_total_pids,
num_total_imgs))
print(" ------------------------------")
self.train = train
self.query = query
self.gallery = gallery
self.num_train_pids = num_train_pids
self.num_query_pids = num_query_pids
self.num_gallery_pids = num_gallery_pids