v1.2.4

README.rst

@@ -33,6 +33,7 @@ You can find some research projects that are built on top of Torchreid `here <ht
 
 What's new
 ------------
+- [Jun 2020] ``1.2.4``: Dataloader's output from ``__getitem__`` has been changed from ``list`` to ``dict``. Previously, an element, e.g. image tensor, was fetched with ``imgs=data[0]``. Now it should be obtained by ``imgs=data['img']``. See this `commit <https://github.com/KaiyangZhou/deep-person-reid/commit/aefe335d68f39a20160860e6d14c2d34f539b8a5>`_ for detailed changes.
 - [May 2020] Added the person attribute recognition code used in `Omni-Scale Feature Learning for Person Re-Identification (ICCV'19) <https://arxiv.org/abs/1905.00953>`_. See ``projects/attribute_recognition/``.
 - [May 2020] ``1.2.1``: Added a simple API for feature extraction (``torchreid/utils/feature_extractor.py``). See the `documentation <https://kaiyangzhou.github.io/deep-person-reid/user_guide.html>`_ for the instruction.
 - [Apr 2020] Code for reproducing the experiments of `deep mutual learning <https://zpascal.net/cvpr2018/Zhang_Deep_Mutual_Learning_CVPR_2018_paper.pdf>`_ in the `OSNet paper <https://arxiv.org/pdf/1905.00953v6.pdf>`__ (Supp. B) has been released at ``projects/DML``.

tools/compute_mean_std.py

@@ -42,7 +42,7 @@ def main():
     std = 0.
     n_samples = 0.
     for data in train_loader:
-        data = data[0]
+        data = data['img']
         batch_size = data.size(0)
         data = data.view(batch_size, data.size(1), -1)
         mean += data.mean(2).sum(0)

tools/visualize_actmap.py

@@ -48,7 +48,7 @@ def visactmap(
         print('Visualizing activation maps for {} ...'.format(target))
 
         for batch_idx, data in enumerate(data_loader):
-            imgs, paths = data[0], data[3]
+            imgs, paths = data['img'], data['impath']
             if use_gpu:
                 imgs = imgs.cuda()
 

torchreid/__init__.py

@@ -2,7 +2,7 @@ from __future__ import print_function, absolute_import
 
 from torchreid import data, optim, utils, engine, losses, models, metrics
 
-__version__ = '1.2.3'
+__version__ = '1.2.4'
 __author__ = 'Kaiyang Zhou'
 __homepage__ = 'https://kaiyangzhou.github.io/'
 __description__ = 'Deep learning person re-identification in PyTorch'

torchreid/data/datasets/dataset.py

@@ -265,12 +265,7 @@ class ImageDataset(Dataset):
         img = read_image(img_path)
         if self.transform is not None:
             img = self.transform(img)
-        item = {
-            'img': img,
-            'pid': pid,
-            'camid': camid,
-            'impath': img_path
-        }
+        item = {'img': img, 'pid': pid, 'camid': camid, 'impath': img_path}
         return item
 
     def show_summary(self):
@@ -379,11 +374,7 @@ class VideoDataset(Dataset):
             imgs.append(img)
         imgs = torch.cat(imgs, dim=0)
 
-        item = {
-            'img': imgs,
-            'pid': pid,
-            'camid': camid
-        }
+        item = {'img': imgs, 'pid': pid, 'camid': camid}
 
         return item