def imgextract(self):
raw_dir = osp.join(self.root, 'raw')
exdir1 = osp.join(raw_dir, datasetname)
exdir2 = osp.join(raw_dir, flowname)
fpath1 = osp.join(raw_dir, datasetname + '.tar')
fpath2 = osp.join(raw_dir, flowname + '.tar')
if not osp.isdir(exdir1):
print("Extracting tar file")
cwd = os.getcwd()
tar = tarfile.open(fpath1)
mkdir_if_missing(exdir1)
os.chdir(exdir1)
tar.extractall()
tar.close()
os.chdir(cwd)
if not osp.isdir(exdir2):
print("Extracting tar file")
cwd = os.getcwd()
tar = tarfile.open(fpath2)
mkdir_if_missing(exdir2)
os.chdir(exdir2)
tar.extractall()
tar.close()
os.chdir(cwd)
# reorganzing the dataset
# Format
temp_images_dir = osp.join(self.root, 'temp_images')
mkdir_if_missing(temp_images_dir)
temp_others_dir = osp.join(self.root, 'temp_others')
mkdir_if_missing(temp_others_dir)
images_dir = osp.join(self.root, 'images')
mkdir_if_missing(images_dir)
others_dir = osp.join(self.root, 'others')
mkdir_if_missing(others_dir)
fpaths1 = sorted(glob(osp.join(exdir1, 'i-LIDS-VID/sequences', '*/*/*.png')))
fpaths2 = sorted(glob(osp.join(exdir2, flowname, '*/*/*.png')))
identities_imgraw = [[[] for _ in range(2)] for _ in range(319)]
identities_otherraw = [[[] for _ in range(2)] for _ in range(319)]
# image information
for fpath in fpaths1:
fname = osp.basename(fpath)
fname_list = fname.split('_')
cam_name = fname_list[0]
pid_name = fname_list[1]
cam = int(cam_name[-1])
pid = int(pid_name[-3:])
temp_fname = ('{:08d}_{:02d}_{:04d}.png'
.format(pid, cam, len(identities_imgraw[pid - 1][cam - 1])))
identities_imgraw[pid - 1][cam - 1].append(temp_fname)
shutil.copy(fpath, osp.join(temp_images_dir, temp_fname))
identities_temp = [x for x in identities_imgraw if x != [[], []]]
identities_images = identities_temp
for pid in range(len(identities_temp)):
for cam in range(2):
for img in range(len(identities_images[pid][cam])):
temp_fname = identities_temp[pid][cam][img]
fname = ('{:08d}_{:02d}_{:04d}.png'
.format(pid, cam, img))
identities_images[pid][cam][img] = fname
shutil.copy(osp.join(temp_images_dir, temp_fname), osp.join(images_dir, fname))
shutil.rmtree(temp_images_dir)
# flow information
for fpath in fpaths2:
fname = osp.basename(fpath)
fname_list = fname.split('_')
cam_name = fname_list[0]
pid_name = fname_list[1]
cam = int(cam_name[-1])
pid = int(pid_name[-3:])
temp_fname = ('{:08d}_{:02d}_{:04d}.png'
.format(pid, cam, len(identities_otherraw[pid - 1][cam - 1])))
identities_otherraw[pid - 1][cam - 1].append(temp_fname)
shutil.copy(fpath, osp.join(temp_others_dir, temp_fname))
identities_temp = [x for x in identities_otherraw if x != [[], []]]
identities_others = identities_temp
for pid in range(len(identities_temp)):
for cam in range(2):
for img in range(len(identities_others[pid][cam])):
temp_fname = identities_temp[pid][cam][img]
fname = ('{:08d}_{:02d}_{:04d}.png'
.format(pid, cam, img))
identities_others[pid][cam][img] = fname
shutil.copy(osp.join(temp_others_dir, temp_fname), osp.join(others_dir, fname))
shutil.rmtree(temp_others_dir)
meta = {'name': 'iLIDS-sequence', 'shot': 'sequence', 'num_cameras': 2,
'identities': identities_images}
write_json(meta, osp.join(self.root, 'meta.json'))
# Consider fixed training and testing split
splitmat_name = osp.join(exdir1, 'train-test people splits', 'train_test_splits_ilidsvid.mat')
data = sio.loadmat(splitmat_name)
person_list = data['ls_set']
num = len(identities_images)
splits = []
for i in range(10):
pids = (person_list[i] - 1).tolist()
trainval_pids = sorted(pids[:num // 2])
test_pids = sorted(pids[num // 2:])
split = {'trainval': trainval_pids,
'query': test_pids,
'gallery': test_pids}
splits.append(split)
write_json(splits, osp.join(self.root, 'splits.json'))
def imgextract(self):
raw_dir = osp.join(self.root, 'raw')
# raw_dir = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw
exdir1 = osp.join(raw_dir, datasetname)
# exdir1 = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw/prid_2011
exdir2 = osp.join(raw_dir, flowname)
# exdir2 = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw/prid2011flow
fpath1 = osp.join(raw_dir, datasetname + '.tar')
# fpath1 = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw/prid_2011.tar
fpath2 = osp.join(raw_dir, flowname + '.tar')
# fpath2 = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw/prid2011flow.tar
if not osp.isdir(exdir1):
print("Extracting tar file")
cwd = os.getcwd()
tar_ref = tarfile.open(fpath1)
mkdir_if_missing(exdir1)
os.chdir(exdir1)
tar_ref.extractall()
tar_ref.close()
os.chdir(cwd)
if not osp.isdir(exdir2):
print("Extracting tar file")
cwd = os.getcwd()
tar_ref = tarfile.open(fpath2)
mkdir_if_missing(exdir2)
os.chdir(exdir2)
tar_ref.extractall()
tar_ref.close()
os.chdir(cwd)
# recognizing the dataset
# Format
temp_images_dir = osp.join(self.root, 'temp_images')
mkdir_if_missing(temp_images_dir)
temp_others_dir = osp.join(self.root, 'temp_others')
mkdir_if_missing(temp_others_dir)
images_dir = osp.join(self.root, 'images')
mkdir_if_missing(images_dir)
# images_dir = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/images
others_dir = osp.join(self.root, 'others')
mkdir_if_missing(others_dir)
# others_dir = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/others
fpaths1 = sorted(
glob(osp.join(exdir1, 'prid_2011/multi_shot',
'*/*/*.png'))) # 存放所有图片的绝对路径
fpaths2 = sorted(glob(osp.join(exdir2, 'prid2011flow', '*/*/*.png')))
identities_imgraw = [[[] for _ in range(2)]
for _ in range(200)] # 200个[ []..[] ]
identities_otherraw = [[[] for _ in range(2)] for _ in range(200)]
for fpath in fpaths1:
fname = fpath
fname_list = fname.split('/')
cam_name = fname_list[-3] # cam_a / cam_b
pid_name = fname_list[-2] # person_001
frame_name = fname_list[-1] # 0001.png
cam_id = 1 if cam_name == 'cam_a' else 2 # cam_id = 1 / 2
pid_id = int(pid_name.split('_')[-1]) # pid_id = 001
if pid_id > 200:
continue
frame_id = int(frame_name.split('.')[-2]) # frame_id = 0001
temp_fname = ('{:08d}_{:02d}_{:04d}.png'.format(
pid_id - 1, cam_id - 1, frame_id - 1))
identities_imgraw[pid_id - 1][cam_id - 1].append(temp_fname)
shutil.copy(fpath, osp.join(temp_images_dir, temp_fname))
identities_temp = [x for x in identities_imgraw if x != [[], []]]
identities_images = identities_temp
for pid in range(len(identities_temp)):
for cam in range(2):
for img in range(len(identities_images[pid][cam])):
temp_fname = identities_temp[pid][cam][img]
fname = ('{:08d}_{:02d}_{:04d}.png'.format(pid, cam, img))
identities_images[pid][cam][img] = fname
shutil.copy(osp.join(temp_images_dir, temp_fname),
osp.join(images_dir, fname))
shutil.rmtree(temp_images_dir)
for fpath in fpaths2:
fname = fpath
fname_list = fname.split('/')
cam_name = fname_list[-3] # cam_a / cam_b
pid_name = fname_list[-2] # person_001
frame_name = fname_list[-1] # 0001.png
cam_id = 1 if cam_name == 'cam_a' else 2 # cam_id = 1 / 2
pid_id = int(pid_name.split('_')[-1]) # pid_id = 001
if pid_id > 200:
continue
frame_id = int(frame_name.split('.')[-2]) # frame_id = 0001
temp_fname = ('{:08d}_{:02d}_{:04d}.png'.format(
pid_id - 1, cam_id - 1, frame_id - 1))
identities_otherraw[pid_id - 1][cam_id - 1].append(temp_fname)
shutil.copy(fpath, osp.join(temp_others_dir, temp_fname))
identities_temp = [x for x in identities_otherraw if x != [[], []]]
identities_others = identities_temp
for pid in range(len(identities_temp)):
for cam in range(2):
for img in range(len(identities_others[pid][cam])):
temp_fname = identities_temp[pid][cam][img]
fname = ('{:08d}_{:02d}_{:04d}.png'.format(pid, cam, img))
identities_images[pid][cam][img] = fname
shutil.copy(osp.join(temp_others_dir, temp_fname),
osp.join(others_dir, fname))
shutil.rmtree(temp_others_dir)
meta = {
'name': 'prid-sequence',
'shot': 'sequence',
'num_cameras': 2,
'identities': identities_images
}
write_json(meta, osp.join(self.root, 'meta.json'))
# Consider fixed training and testing split
num = len(identities_images)
splits = []
for i in range(20):
pids = np.random.permutation(num)
pids = (pids - 1).tolist()
trainval_pids = pids[:num // 2]
test_pids = pids[num // 2:]
split = {
'trainval': trainval_pids,
'query': test_pids,
'gallery': test_pids
}
splits.append(split)
write_json(splits, osp.join(self.root, 'splits.json'))
def imgextract(self):
raw_dir = osp.join(self.root, 'raw')
# raw_dir = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw
exdir1 = osp.join(raw_dir, datasetname)
# exdir1 = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw/prid_2011
exdir2 = osp.join(raw_dir, flowname)
# exdir2 = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw/prid2011flow
fpath1 = osp.join(raw_dir, datasetname + '.tar')
# fpath1 = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw/prid_2011.tar
fpath2 = osp.join(raw_dir, flowname + '.tar')
# fpath2 = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/raw/prid2011flow.tar
if not osp.isdir(exdir1):
print("Extracting tar file")
cwd = os.getcwd()
tar_ref = tarfile.open(fpath1)
mkdir_if_missing(exdir1)
os.chdir(exdir1)
tar_ref.extractall()
tar_ref.close()
os.chdir(cwd)
if not osp.isdir(exdir2):
print("Extracting tar file")
cwd = os.getcwd()
tar_ref = tarfile.open(fpath2)
mkdir_if_missing(exdir2)
os.chdir(exdir2)
tar_ref.extractall()
tar_ref.close()
os.chdir(cwd)
# recognizing the dataset
# Format
temp_images_dir = osp.join(self.root, 'temp_images')
mkdir_if_missing(temp_images_dir)
temp_others_dir = osp.join(self.root, 'temp_others')
mkdir_if_missing(temp_others_dir)
images_dir = osp.join(self.root, 'images')
mkdir_if_missing(images_dir)
# images_dir = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/images
others_dir = osp.join(self.root, 'others')
mkdir_if_missing(others_dir)
# others_dir = /media/ying/0BDD17830BDD1783/video_reid _prid/data/prid2011sequence/others
fpaths1 = sorted(glob(osp.join(exdir1, 'prid_2011/multi_shot', '*/*/*.png')))
fpaths2 = sorted(glob(osp.join(exdir2, 'prid2011flow', '*/*/*.png')))
identities_imgraw = [[[] for _ in range(2)] for _ in range(200)]
identities_otherraw = [[[] for _ in range(2)] for _ in range(200)]
for fpath in fpaths1:
fname = fpath
fname_list = fname.split('/')
cam_name = fname_list[-3] # cam_a / cam_b
pid_name = fname_list[-2] # person_001
frame_name = fname_list[-1] # 0001.png
cam_id = 1 if cam_name == 'cam_a' else 2 # cam_id = 1 / 2
pid_id = int(pid_name.split('_')[-1]) # pid_id = 001
if pid_id > 200:
continue
frame_id = int(frame_name.split('.')[-2]) # frame_id = 0001
temp_fname = ('{:08d}_{:02d}_{:04d}.png'
.format(pid_id-1, cam_id-1, frame_id-1))
identities_imgraw[pid_id - 1][cam_id - 1].append(temp_fname)
shutil.copy(fpath, osp.join(temp_images_dir, temp_fname))
identities_temp = [x for x in identities_imgraw if x != [[], []]]
identities_images = identities_temp
for pid in range(len(identities_temp)):
for cam in range(2):
for img in range(len(identities_images[pid][cam])):
temp_fname = identities_temp[pid][cam][img]
fname = ('{:08d}_{:02d}_{:04d}.png'.format(pid, cam, img))
identities_images[pid][cam][img] = fname
shutil.copy(osp.join(temp_images_dir, temp_fname), osp.join(images_dir, fname))
shutil.rmtree(temp_images_dir)
for fpath in fpaths2:
fname = fpath
fname_list = fname.split('/')
cam_name = fname_list[-3] # cam_a / cam_b
pid_name = fname_list[-2] # person_001
frame_name = fname_list[-1] # 0001.png
cam_id = 1 if cam_name == 'cam_a' else 2 # cam_id = 1 / 2
pid_id = int(pid_name.split('_')[-1]) # pid_id = 001
if pid_id > 200:
continue
frame_id = int(frame_name.split('.')[-2]) # frame_id = 0001
temp_fname = ('{:08d}_{:02d}_{:04d}.png'
.format(pid_id-1, cam_id-1, frame_id-1))
identities_otherraw[pid_id - 1][cam_id - 1].append(temp_fname)
shutil.copy(fpath, osp.join(temp_others_dir, temp_fname))
identities_temp = [x for x in identities_otherraw if x != [[], []]]
identities_others = identities_temp
for pid in range(len(identities_temp)):
for cam in range(2):
for img in range(len(identities_others[pid][cam])):
temp_fname = identities_temp[pid][cam][img]
fname = ('{:08d}_{:02d}_{:04d}.png'.format(pid, cam, img))
identities_images[pid][cam][img] = fname
shutil.copy(osp.join(temp_others_dir, temp_fname), osp.join(others_dir, fname))
shutil.rmtree(temp_others_dir)
meta = {'name': 'prid-sequence', 'shot': 'sequence', 'num_cameras': 2,
'identities': identities_images}
write_json(meta, osp.join(self.root, 'meta.json'))
# Consider fixed training and testing split
num = 200
splits = []
for i in range(10):
pids = np.random.permutation(num)
pids = (pids - 1).tolist()
trainval_pids = pids[:num // 2]
test_pids = pids[num // 2:]
split = {'trainval': trainval_pids,
'query': test_pids,
'gallery': test_pids}
splits.append(split)
write_json(splits, osp.join(self.root, 'splits.json'))
def imgextract(self):
raw_dir = osp.join(self.root, 'raw')
exdir1 = osp.join(raw_dir, datasetname)
exdir2 = osp.join(raw_dir, flowname)
fpath1 = osp.join(raw_dir, datasetname + '.tar')
fpath2 = osp.join(raw_dir, flowname + '.tar')
if not osp.isdir(exdir1):
print("Extracting tar file")
cwd = os.getcwd()
tar = tarfile.open(fpath1)
mkdir_if_missing(exdir1)
os.chdir(exdir1)
tar.extractall()
tar.close()
os.chdir(cwd)
if not osp.isdir(exdir2):
print("Extracting tar file")
cwd = os.getcwd()
tar = tarfile.open(fpath2)
mkdir_if_missing(exdir2)
os.chdir(exdir2)
tar.extractall()
tar.close()
os.chdir(cwd)
# reorganzing the dataset
# Format
temp_images_dir = osp.join(self.root, 'temp_images')
mkdir_if_missing(temp_images_dir)
temp_others_dir = osp.join(self.root, 'temp_others')
mkdir_if_missing(temp_others_dir)
images_dir = osp.join(self.root, 'images')
mkdir_if_missing(images_dir)
others_dir = osp.join(self.root, 'others')
mkdir_if_missing(others_dir)
fpaths1 = sorted(
glob(osp.join(exdir1, 'i-LIDS-VID/sequences', '*/*/*.png')))
fpaths2 = sorted(glob(osp.join(exdir2, flowname, '*/*/*.png')))
identities_imgraw = [[[] for _ in range(2)] for _ in range(319)]
identities_otherraw = [[[] for _ in range(2)] for _ in range(319)]
# image information
for fpath in fpaths1:
fname = osp.basename(fpath)
fname_list = fname.split('_')
cam_name = fname_list[0]
pid_name = fname_list[1]
cam = int(cam_name[-1])
pid = int(pid_name[-3:])
temp_fname = ('{:08d}_{:02d}_{:04d}.png'.format(
pid, cam, len(identities_imgraw[pid - 1][cam - 1])))
identities_imgraw[pid - 1][cam - 1].append(temp_fname)
shutil.copy(fpath, osp.join(temp_images_dir, temp_fname))
identities_temp = [x for x in identities_imgraw if x != [[], []]]
identities_images = identities_temp
for pid in range(len(identities_temp)):
for cam in range(2):
for img in range(len(identities_images[pid][cam])):
temp_fname = identities_temp[pid][cam][img]
fname = ('{:08d}_{:02d}_{:04d}.png'.format(
pid, cam, img))
identities_images[pid][cam][img] = fname
shutil.copy(osp.join(temp_images_dir, temp_fname),
osp.join(images_dir, fname))
shutil.rmtree(temp_images_dir)
# flow information
for fpath in fpaths2:
fname = osp.basename(fpath)
fname_list = fname.split('_')
cam_name = fname_list[0]
pid_name = fname_list[1]
cam = int(cam_name[-1])
pid = int(pid_name[-3:])
temp_fname = ('{:08d}_{:02d}_{:04d}.png'.format(
pid, cam, len(identities_otherraw[pid - 1][cam - 1])))
identities_otherraw[pid - 1][cam - 1].append(temp_fname)
shutil.copy(fpath, osp.join(temp_others_dir, temp_fname))
identities_temp = [x for x in identities_otherraw if x != [[], []]]
identities_others = identities_temp
for pid in range(len(identities_temp)):
for cam in range(2):
for img in range(len(identities_others[pid][cam])):
temp_fname = identities_temp[pid][cam][img]
fname = ('{:08d}_{:02d}_{:04d}.png'.format(
pid, cam, img))
identities_others[pid][cam][img] = fname
shutil.copy(osp.join(temp_others_dir, temp_fname),
osp.join(others_dir, fname))
shutil.rmtree(temp_others_dir)
meta = {
'name': 'iLIDS-sequence',
'shot': 'sequence',
'num_cameras': 2,
'identities': identities_images
}
write_json(meta, osp.join(self.root, 'meta.json'))
# Consider fixed training and testing split
splitmat_name = osp.join(exdir1, 'train-test people splits',
'train_test_splits_ilidsvid.mat')
data = sio.loadmat(splitmat_name)
person_list = data['ls_set']
num = len(identities_images)
splits = []
for i in range(10):
pids = (person_list[i] - 1).tolist()
trainval_pids = sorted(pids[:num // 2])
test_pids = sorted(pids[num // 2:])
split = {
'trainval': trainval_pids,
'query': test_pids,
'gallery': test_pids
}
splits.append(split)
write_json(splits, osp.join(self.root, 'splits.json'))
def imgextract(self):
raw_dir = osp.join(self.root, 'raw')
exdir1 = osp.join(raw_dir, datasetname)
exdir2 = osp.join(raw_dir, flowname)
fpath1 = osp.join(raw_dir, datasetname + '.zip')
fpath2 = osp.join(raw_dir, flowname + '.tar')
if not osp.isdir(exdir1):
print("Extracting tar file")
cwd = os.getcwd()
zip_ref = zipfile.ZipFile(fpath1, 'r')
mkdir_if_missing(exdir1)
zip_ref.extractall(exdir1)
zip_ref.close()
os.chdir(cwd)
if not osp.isdir(exdir2):
print("Extracting tar file")
cwd = os.getcwd()
tar_ref = tarfile.open(fpath2)
mkdir_if_missing(exdir2)
os.chdir(exdir2)
tar_ref.extractall()
tar_ref.close()
os.chdir(cwd)
## recognizing the dataset
# Format
images_dir = osp.join(self.root, 'images')
mkdir_if_missing(images_dir)
others_dir = osp.join(self.root, 'others')
mkdir_if_missing(others_dir)
fpaths1 = sorted(glob(osp.join(exdir1, 'multi_shot', '*/*/*.png')))
fpaths2 = sorted(glob(osp.join(exdir2, '*/*.png')))
identities_images = [[[] for _ in range(2)] for _ in range(200)]
for fpath in fpaths1:
fname = fpath
fname_list = fname.split('/')
cam_name = fname_list[-3]
pid_name = fname_list[-2]
frame_name = fname_list[-1]
cam_id = 1 if cam_name =='cam_a' else 2
pid_id = int(pid_name.split('_')[-1])
if pid_id > 200:
continue
frame_id = int(frame_name.split('.')[-2])
imagefname = ('{:08d}_{:02d}_{:04d}.png'
.format(pid_id-1, cam_id-1, frame_id-1))
identities_images[pid_id - 1][cam_id - 1].append(imagefname)
shutil.copy(fpath, osp.join(images_dir, imagefname))
for fpath in fpaths2:
fname = fpath
fname_list = fname.split('/')
fname_img = fname_list[-1]
shutil.copy(fname, osp.join(others_dir, fname_img))
meta = {'name': 'iLIDS-sequence', 'shot': 'sequence', 'num_cameras': 2,
'identities': identities_images}
write_json(meta, osp.join(self.root, 'meta.json'))
# Consider fixed training and testing split
num = 200
splits = []
for i in range(10):
pids = np.random.permutation(num)
pids = (pids -1).tolist()
trainval_pids = pids[:num // 2]
test_pids = pids[num // 2:]
split = {'trainval': trainval_pids,
'query': test_pids,
'gallery': test_pids}
splits.append(split)
write_json(splits, osp.join(self.root, 'splits.json'))
def _process_dir_dense(self,
dir_path,
json_path,
relabel,
sampling_step=32):
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)
# dense sampling
num_sampling = len(img_paths) // sampling_step
if num_sampling == 0:
tracklets.append((img_paths, pid, camid))
else:
for idx in range(num_sampling):
if idx == num_sampling - 1:
tracklets.append(
(img_paths[idx * sampling_step:], pid, camid))
else:
tracklets.append(
(img_paths[idx * sampling_step:(idx + 1) *
sampling_step], 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 _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 得到数据集中的所有文件夹
print("Processing {} with {} person identities".format(
dir_path, len(pdirs)))
pid_container = set() # 得到文件夹的名字，即行人的id，集合的形式，一共有702个文件夹，即702个行人id
for pdir in pdirs:
pid = int(osp.basename(pdir))
pid_container.add(pid)
pid2label = {pid: label
for label, pid in enumerate(pid_container)} # relabel。。
tracklets = []
num_imgs_per_tracklet = [] # 存放每个tracklet的图片数目的列表
for pdir in pdirs: # 遍历每个子文件夹，得到其中的图片，即每个id对应的视频图片集
pid = int(osp.basename(pdir)) # pid=817.。
if relabel: pid = pid2label[pid] # relabel。。
tdirs = glob.glob(osp.join(pdir,
'*')) # 得到文件夹中的所有tracklets，一个id有多个视频序列
for tdir in tdirs:
raw_img_paths = glob.glob(osp.join(
tdir, '*.jpg')) # 得到每个tracklet中图片的绝对路径，乱序
num_imgs = len(raw_img_paths) # 162 tracklet的长度=图片的数目
if num_imgs < self.min_seq_len:
continue
num_imgs_per_tracklet.append(num_imgs)
img_paths = []
for img_idx in range(
num_imgs): # 在这里，将每个tracklet中图片的乱序索引，进行排序。
# some tracklet starts from 0002 instead of 0001
img_idx_name = 'F' + str(img_idx + 1).zfill(4) # F0001
res = glob.glob(
osp.join(tdir, '*' + img_idx_name +
'*.jpg')) # 找到对应img索引的图片的绝对路径
if len(res) == 0: # 有些帧的索引可能不存在，这时需要跳过
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]) # 图片的格式：'0817_C1_F0001_X207382.jpg'
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)) # 得到每个tracklet的所有图片的绝对路径，行人id，camid =》 和Mars数据集类似
num_pids = len(pid_container) # 训练集中的id数目
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 _process_gallery_data(self,
names,
meta_data,
home_dir=None,
relabel=False,
min_seq_len=0,
json_path=''):
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'], split[
'pids'], split['camid']
assert home_dir in ['bbox_train', 'bbox_test']
num_tracklets = meta_data.shape[0] # 8298 TODO: 要不要增加?
pid_list = list(set(
meta_data[:, 2].tolist())) # pid = 625 => [1 3 5 7 9...]
num_pids = len(pid_list) # 626 622
if relabel:
pid2label = {pid: label
for label, pid in enumerate(pid_list)
} # {1:0,3:1,5:2,...}
tracklets = []
num_imgs_per_tracklet = []
gallery_pid = []
gallery_camid = []
for tracklet_idx in range(num_tracklets):
data = meta_data[tracklet_idx, ...] # [1 16 1 1]
start_index, end_index, pid, camid = data
if pid == -1:
continue # junk images are just ignored
assert 1 <= camid <= 6
if relabel:
pid = pid2label[pid] # pid = 0
camid -= 1
# index starts from 0
img_names = names[start_index - 1:end_index]
# <class 'list'>:['0001C1T0001F001.jpg'.. '0001C1T0001F016.jpg']
# make sure image names correspond to the same person
pnames = [img_name[:4]
for img_name in img_names] # pnames = ['0001','0001'...]
assert len(
set(pnames)
) == 1, "Error: a single tracklet contains different person images"
# make sure all images are captured under the same camera
camnames = [img_name[5]
for img_name in img_names] # camnames = ['1','1'...]
assert len(
set(camnames)
) == 1, "Error: images are captured under different cameras!"
# append image names with directory information
# '/media/ying/0BDD17830BDD1783/ReIdDataset/Mars/bbox_train/0001/0001C1T0001F001.jpg'
img_paths = [
osp.join(self.root, home_dir, img_name[:4], img_name)
for img_name in img_names
] # list<16>
if len(img_paths) >= min_seq_len:
img_paths = tuple(img_paths)
tracklets.append(
(img_paths, int(pid), int(camid)
)) # (('.jpg','.jpg','每张图片的路径'), 0'行人id', 0'camid' )
num_imgs_per_tracklet.append(
len(img_paths)) # [16,79,15...'每个小段视频包含的图片帧数目']
gallery_pid.append(int(pid))
gallery_camid.append(int(camid))
num_tracklets = len(tracklets) # 8298
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,
'pids': gallery_pid,
'camid': gallery_camid,
}
write_json(split_dict, json_path)
return tracklets, num_tracklets, num_pids, num_imgs_per_tracklet, gallery_pid, gallery_camid