Merge pull request #417 from layumi/master

Add one new dataset University-1652

README.rst

@@ -33,6 +33,7 @@ You can find some research projects that are built on top of Torchreid `here <ht
 
 What's new
 ------------
+- [Feb 2021] We support the new multi-view multi-source geo-localization dataset `University-1652 <https://dl.acm.org/doi/abs/10.1145/3394171.3413896>`_.
 - [Feb 2021] ``v1.3.5``: Now the `cython code <https://github.com/KaiyangZhou/deep-person-reid/pull/412>`_ works on Windows (credit to `lablabla <https://github.com/lablabla>`_).
 - [Jan 2021] Our recent work, `MixStyle <https://openreview.net/forum?id=6xHJ37MVxxp>`_ (mixing instance-level feature statistics of samples of different domains for improving domain generalization), has been accepted to ICLR'21. The code has been released at https://github.com/KaiyangZhou/mixstyle-release where the person re-ID part is based on Torchreid.
 - [Jan 2021] A new evaluation metric called `mean Inverse Negative Penalty (mINP)` for person re-ID has been introduced in `Deep Learning for Person Re-identification: A Survey and Outlook (TPAMI 2021) <https://arxiv.org/abs/2001.04193>`_. Their code can be accessed at `<https://github.com/mangye16/ReID-Survey>`_.
@@ -230,6 +231,10 @@ Image-reid datasets
 - `QMUL-iLIDS <http://www.eecs.qmul.ac.uk/~sgg/papers/ZhengGongXiang_BMVC09.pdf>`_
 - `PRID <https://pdfs.semanticscholar.org/4c1b/f0592be3e535faf256c95e27982db9b3d3d3.pdf>`_
 
+Geo-localization datasets
+^^^^^^^^^^^^^^^^^^^^^^^
+- `University-1652 <https://dl.acm.org/doi/abs/10.1145/3394171.3413896>`_
+
 Video-reid datasets
 ^^^^^^^^^^^^^^^^^^^^^^^
 - `MARS <http://www.liangzheng.org/1320.pdf>`_

torchreid/data/datasets/__init__.py

@@ -2,7 +2,7 @@ from __future__ import print_function, absolute_import
 
 from .image import (
     GRID, PRID, CUHK01, CUHK02, CUHK03, MSMT17, VIPeR, SenseReID, Market1501,
-    DukeMTMCreID, iLIDS
+    DukeMTMCreID, iLIDS, University1652
 )
 from .video import PRID2011, Mars, DukeMTMCVidReID, iLIDSVID
 from .dataset import Dataset, ImageDataset, VideoDataset
@@ -18,7 +18,8 @@ __image_datasets = {
     'ilids': iLIDS,
     'sensereid': SenseReID,
     'prid': PRID,
-    'cuhk02': CUHK02
+    'cuhk02': CUHK02,
+    'university1652':University1652
 }
 
 __video_datasets = {

torchreid/data/datasets/image/__init__.py

@@ -11,3 +11,4 @@ from .msmt17 import MSMT17
 from .sensereid import SenseReID
 from .market1501 import Market1501
 from .dukemtmcreid import DukeMTMCreID
+from .university1652 import University1652

torchreid/data/datasets/image/university1652.py

@@ -0,0 +1,102 @@
+from __future__ import division, print_function, absolute_import
+import re
+import glob
+import os.path as osp
+import os
+import gdown
+
+from ..dataset import ImageDataset
+
+
+class University1652(ImageDataset):
+    """University-1652.
+
+    Reference:
+        - Zheng et al. University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization. ACM MM 2020.
+
+    URL: `<https://github.com/layumi/University1652-Baseline>`_
+OneDrive:
+https://studentutsedu-my.sharepoint.com/:u:/g/personal/12639605_student_uts_edu_au/Ecrz6xK-PcdCjFdpNb0T0s8B_9J5ynaUy3q63_XumjJyrA?e=z4hpcz
+[Backup] GoogleDrive:
+https://drive.google.com/file/d/1iVnP4gjw-iHXa0KerZQ1IfIO0i1jADsR/view?usp=sharing
+[Backup] Baidu Yun:
+https://pan.baidu.com/s/1H_wBnWwikKbaBY1pMPjoqQ password: hrqp
+    
+    Dataset statistics:
+        - buildings: 1652 (train + query).
+        - The dataset split is as follows: 
+| Split | #imgs | #buildings | #universities|
+| --------   | -----  | ----| ----|
+| Training | 50,218 | 701 | 33 |
+| Query_drone | 37,855 | 701 |  39 |
+| Query_satellite | 701 | 701 | 39|
+| Query_ground | 2,579 | 701 | 39|
+| Gallery_drone | 51,355 | 951 | 39|
+| Gallery_satellite |  951 | 951 | 39|
+| Gallery_ground | 2,921 | 793  | 39|
+        - cameras: None.
+datamanager = torchreid.data.ImageDataManager(
+    root='reid-data',
+    sources='university1652',
+    targets='university1652',
+    height=256,
+    width=256,
+    batch_size_train=32,
+    batch_size_test=100,
+    transforms=['random_flip', 'random_crop']
+)
+    """
+    dataset_dir = 'university1652'
+    dataset_url = 'https://drive.google.com/uc?id=1iVnP4gjw-iHXa0KerZQ1IfIO0i1jADsR'
+    def __init__(self, root='', **kwargs):
+        self.root = osp.abspath(osp.expanduser(root))
+        self.dataset_dir = osp.join(self.root, self.dataset_dir)
+        print(self.dataset_dir)
+        if not os.path.isdir(self.dataset_dir):
+            os.mkdir(self.dataset_dir)
+            gdown.download(self.dataset_url, self.dataset_dir+'data.zip', quiet=False)
+            os.system('unzip %s'%(self.dataset_dir+'data.zip'))
+        self.train_dir = osp.join(
+            self.dataset_dir,'University-Release/train/'
+        )
+        self.query_dir = osp.join(self.dataset_dir, 'University-Release/test/query_drone')
+        self.gallery_dir = osp.join(
+            self.dataset_dir, 'University-Release/test/gallery_satellite'
+        )
+
+        required_files = [
+            self.dataset_dir, self.train_dir, self.query_dir, self.gallery_dir
+        ]
+        self.check_before_run(required_files)
+
+        self.fake_camid = 0
+        train = self.process_dir(self.train_dir, relabel=True, train=True)
+        query = self.process_dir(self.query_dir, relabel=False)
+        gallery = self.process_dir(self.gallery_dir, relabel=False)
+
+        super(University1652, self).__init__(train, query, gallery, **kwargs)
+
+    def process_dir(self, dir_path, relabel=False, train=False):
+        IMG_EXTENSIONS = ('.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif', '.tiff', '.webp')
+        if train:
+            img_paths = glob.glob(osp.join(dir_path, '*/*/*'))
+        else:
+            img_paths = glob.glob(osp.join(dir_path, '*/*'))
+        pid_container = set()
+        for img_path in img_paths:
+            if not img_path.lower().endswith(IMG_EXTENSIONS):
+                continue
+            pid = int(os.path.basename(os.path.dirname(img_path))) 
+            pid_container.add(pid)
+        pid2label = {pid: label for label, pid in enumerate(pid_container)}
+        data = []
+        # no camera for university
+        for img_path in img_paths:
+            if not img_path.lower().endswith(IMG_EXTENSIONS):
+                continue
+            pid = int(os.path.basename(os.path.dirname(img_path))) 
+            if relabel:
+                pid = pid2label[pid]
+            data.append((img_path, pid, self.fake_camid))
+            self.fake_camid +=1
+        return data