fast-reid/fastreid/data/datasets/dukemtmcreid.py

71 lines
2.3 KiB
Python

# encoding: utf-8
"""
@author: liaoxingyu
@contact: liaoxingyu2@jd.com
"""
import glob
import os.path as osp
import re
from .bases import ImageDataset
from ..datasets import DATASET_REGISTRY
@DATASET_REGISTRY.register()
class DukeMTMC(ImageDataset):
"""DukeMTMC-reID.
Reference:
- Ristani et al. Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. ECCVW 2016.
- Zheng et al. Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro. ICCV 2017.
URL: `<https://github.com/layumi/DukeMTMC-reID_evaluation>`_
Dataset statistics:
- identities: 1404 (train + query).
- images:16522 (train) + 2228 (query) + 17661 (gallery).
- cameras: 8.
"""
dataset_dir = 'DukeMTMC-reID'
dataset_url = 'http://vision.cs.duke.edu/DukeMTMC/data/misc/DukeMTMC-reID.zip'
dataset_name = "dukemtmc"
def __init__(self, root='datasets', **kwargs):
# self.root = osp.abspath(osp.expanduser(root))
self.root = root
self.dataset_dir = osp.join(self.root, self.dataset_dir)
self.train_dir = osp.join(self.dataset_dir, 'bounding_box_train')
self.query_dir = osp.join(self.dataset_dir, 'query')
self.gallery_dir = osp.join(self.dataset_dir, 'bounding_box_test')
required_files = [
self.dataset_dir,
self.train_dir,
self.query_dir,
self.gallery_dir,
]
self.check_before_run(required_files)
train = self.process_dir(self.train_dir)
query = self.process_dir(self.query_dir, is_train=False)
gallery = self.process_dir(self.gallery_dir, is_train=False)
super(DukeMTMC, self).__init__(train, query, gallery, **kwargs)
def process_dir(self, dir_path, is_train=True):
img_paths = glob.glob(osp.join(dir_path, '*.jpg'))
pattern = re.compile(r'([-\d]+)_c(\d)')
data = []
for img_path in img_paths:
pid, camid = map(int, pattern.search(img_path).groups())
assert 1 <= camid <= 8
camid -= 1 # index starts from 0
if is_train:
pid = self.dataset_name + "_" + str(pid)
camid = self.dataset_name + "_" + str(camid)
data.append((img_path, pid, camid))
return data