189 lines
7.8 KiB
Python
189 lines
7.8 KiB
Python
from __future__ import print_function, absolute_import
|
|
|
|
import os
|
|
import glob
|
|
import re
|
|
import sys
|
|
import urllib
|
|
import tarfile
|
|
import zipfile
|
|
import os.path as osp
|
|
from scipy.io import loadmat
|
|
import numpy as np
|
|
import h5py
|
|
from scipy.misc import imsave
|
|
|
|
from utils.iotools import mkdir_if_missing, write_json, read_json
|
|
|
|
|
|
class iLIDSVID(object):
|
|
"""
|
|
iLIDS-VID
|
|
|
|
Reference:
|
|
Wang et al. Person Re-Identification by Video Ranking. ECCV 2014.
|
|
|
|
URL: http://www.eecs.qmul.ac.uk/~xiatian/downloads_qmul_iLIDS-VID_ReID_dataset.html
|
|
|
|
Dataset statistics:
|
|
# identities: 300
|
|
# tracklets: 600
|
|
# cameras: 2
|
|
"""
|
|
dataset_dir = 'ilids-vid'
|
|
|
|
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 _download_data(self):
|
|
if osp.exists(self.dataset_dir):
|
|
print("This dataset has been downloaded.")
|
|
return
|
|
|
|
mkdir_if_missing(self.dataset_dir)
|
|
fpath = osp.join(self.dataset_dir, osp.basename(self.dataset_url))
|
|
|
|
print("Downloading iLIDS-VID dataset")
|
|
urllib.urlretrieve(self.dataset_url, fpath)
|
|
|
|
print("Extracting files")
|
|
tar = tarfile.open(fpath)
|
|
tar.extractall(path=self.dataset_dir)
|
|
tar.close()
|
|
|
|
def _check_before_run(self):
|
|
"""Check if all files are available before going deeper"""
|
|
if not osp.exists(self.dataset_dir):
|
|
raise RuntimeError("'{}' is not available".format(self.dataset_dir))
|
|
if not osp.exists(self.data_dir):
|
|
raise RuntimeError("'{}' is not available".format(self.data_dir))
|
|
if not osp.exists(self.split_dir):
|
|
raise RuntimeError("'{}' is not available".format(self.split_dir))
|
|
|
|
def _prepare_split(self):
|
|
if not osp.exists(self.split_path):
|
|
print("Creating splits")
|
|
mat_split_data = loadmat(self.split_mat_path)['ls_set']
|
|
|
|
num_splits = mat_split_data.shape[0]
|
|
num_total_ids = mat_split_data.shape[1]
|
|
assert num_splits == 10
|
|
assert num_total_ids == 300
|
|
num_ids_each = num_total_ids/2
|
|
|
|
# pids in mat_split_data are indices, so we need to transform them
|
|
# to real pids
|
|
person_cam1_dirs = sorted(glob.glob(osp.join(self.cam_1_path, '*')))
|
|
person_cam2_dirs = sorted(glob.glob(osp.join(self.cam_2_path, '*')))
|
|
|
|
person_cam1_dirs = [osp.basename(item) for item in person_cam1_dirs]
|
|
person_cam2_dirs = [osp.basename(item) for item in person_cam2_dirs]
|
|
|
|
# make sure persons in one camera view can be found in the other camera view
|
|
assert set(person_cam1_dirs) == set(person_cam2_dirs)
|
|
|
|
splits = []
|
|
for i_split in range(num_splits):
|
|
# first 50% for testing and the remaining for training, following Wang et al. ECCV'14.
|
|
train_idxs = sorted(list(mat_split_data[i_split,num_ids_each:]))
|
|
test_idxs = sorted(list(mat_split_data[i_split,:num_ids_each]))
|
|
|
|
train_idxs = [int(i)-1 for i in train_idxs]
|
|
test_idxs = [int(i)-1 for i in test_idxs]
|
|
|
|
# transform pids to person dir names
|
|
train_dirs = [person_cam1_dirs[i] for i in train_idxs]
|
|
test_dirs = [person_cam1_dirs[i] for i in test_idxs]
|
|
|
|
split = {'train': train_dirs, 'test': test_dirs}
|
|
splits.append(split)
|
|
|
|
print("Totally {} splits are created, following Wang et al. ECCV'14".format(len(splits)))
|
|
print("Split file is saved to {}".format(self.split_path))
|
|
write_json(splits, self.split_path)
|
|
|
|
print("Splits created")
|
|
|
|
def _process_data(self, dirnames, cam1=True, cam2=True):
|
|
tracklets = []
|
|
num_imgs_per_tracklet = []
|
|
dirname2pid = {dirname:i for i, dirname in enumerate(dirnames)}
|
|
|
|
for dirname in dirnames:
|
|
if cam1:
|
|
person_dir = osp.join(self.cam_1_path, dirname)
|
|
img_names = glob.glob(osp.join(person_dir, '*.png'))
|
|
assert len(img_names) > 0
|
|
img_names = tuple(img_names)
|
|
pid = dirname2pid[dirname]
|
|
tracklets.append((img_names, pid, 0))
|
|
num_imgs_per_tracklet.append(len(img_names))
|
|
|
|
if cam2:
|
|
person_dir = osp.join(self.cam_2_path, dirname)
|
|
img_names = glob.glob(osp.join(person_dir, '*.png'))
|
|
assert len(img_names) > 0
|
|
img_names = tuple(img_names)
|
|
pid = dirname2pid[dirname]
|
|
tracklets.append((img_names, pid, 1))
|
|
num_imgs_per_tracklet.append(len(img_names))
|
|
|
|
num_tracklets = len(tracklets)
|
|
num_pids = len(dirnames)
|
|
|
|
return tracklets, num_tracklets, num_pids, num_imgs_per_tracklet |