deep-person-reid/data_manager/prid2011.py

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 PRID2011(object):
    """
    PRID2011

    Reference:
    Hirzer et al. Person Re-Identification by Descriptive and Discriminative Classification. SCIA 2011.

    URL: https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/PRID11/
    
    Dataset statistics:
    # identities: 200
    # tracklets: 400
    # cameras: 2
    """
    dataset_dir = 'prid2011'

    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 _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))

    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_a_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_b_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