Source code for torchreid.data.datasets.image.msmt17

from __future__ import division, print_function, absolute_import
import os.path as osp

from ..dataset import ImageDataset

# Log
# 22.01.2019
# - add v2
# - v1 and v2 differ in dir names
# - note that faces in v2 are blurred
TRAIN_DIR_KEY = 'train_dir'
TEST_DIR_KEY = 'test_dir'
VERSION_DICT = {
    'MSMT17_V1': {
        TRAIN_DIR_KEY: 'train',
        TEST_DIR_KEY: 'test',
    },
    'MSMT17_V2': {
        TRAIN_DIR_KEY: 'mask_train_v2',
        TEST_DIR_KEY: 'mask_test_v2',
    }
}


[docs]class MSMT17(ImageDataset): """MSMT17. Reference: Wei et al. Person Transfer GAN to Bridge Domain Gap for Person Re-Identification. CVPR 2018. URL: `<http://www.pkuvmc.com/publications/msmt17.html>`_ Dataset statistics: - identities: 4101. - images: 32621 (train) + 11659 (query) + 82161 (gallery). - cameras: 15. """ dataset_dir = 'msmt17' dataset_url = None def __init__(self, root='', **kwargs): self.root = osp.abspath(osp.expanduser(root)) self.dataset_dir = osp.join(self.root, self.dataset_dir) self.download_dataset(self.dataset_dir, self.dataset_url) has_main_dir = False for main_dir in VERSION_DICT: if osp.exists(osp.join(self.dataset_dir, main_dir)): train_dir = VERSION_DICT[main_dir][TRAIN_DIR_KEY] test_dir = VERSION_DICT[main_dir][TEST_DIR_KEY] has_main_dir = True break assert has_main_dir, 'Dataset folder not found' self.train_dir = osp.join(self.dataset_dir, main_dir, train_dir) self.test_dir = osp.join(self.dataset_dir, main_dir, test_dir) self.list_train_path = osp.join( self.dataset_dir, main_dir, 'list_train.txt' ) self.list_val_path = osp.join( self.dataset_dir, main_dir, 'list_val.txt' ) self.list_query_path = osp.join( self.dataset_dir, main_dir, 'list_query.txt' ) self.list_gallery_path = osp.join( self.dataset_dir, main_dir, 'list_gallery.txt' ) required_files = [self.dataset_dir, self.train_dir, self.test_dir] self.check_before_run(required_files) train = self.process_dir(self.train_dir, self.list_train_path) val = self.process_dir(self.train_dir, self.list_val_path) query = self.process_dir(self.test_dir, self.list_query_path) gallery = self.process_dir(self.test_dir, self.list_gallery_path) # Note: to fairly compare with published methods on the conventional ReID setting, # do not add val images to the training set. if 'combineall' in kwargs and kwargs['combineall']: train += val super(MSMT17, self).__init__(train, query, gallery, **kwargs) def process_dir(self, dir_path, list_path): with open(list_path, 'r') as txt: lines = txt.readlines() data = [] for img_idx, img_info in enumerate(lines): img_path, pid = img_info.split(' ') pid = int(pid) # no need to relabel camid = int(img_path.split('_')[2]) - 1 # index starts from 0 img_path = osp.join(dir_path, img_path) data.append((img_path, pid, camid)) return data