mirrors
/
deep-person-reid
mirror of https://github.com/KaiyangZhou/deep-person-reid.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

update readme

pull/417/head
KaiyangZhou 2021-02-09 21:27:40 +08:00
parent d064f4c966
commit 08a993b123
1 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
README.rst
View File

@ -33,17 +33,18 @@ You can find some research projects that are built on top of Torchreid `here <ht
What's new
------------
- [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 experiments on person re-ID are based on Torchreid.
- [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>`_.
- [Aug 2020] ``1.3.3``: Fixed bug in ``visrank`` (caused by not unpacking ``dsetid``).
- [Aug 2020] ``1.3.2``: Added ``_junk_pids`` to ``grid`` and ``prid``. This avoids using mislabeled gallery images for training when setting ``combineall=True``.
- [Aug 2020] ``1.3.0``: (1) Added ``dsetid`` to the existing 3-tuple data source, resulting in ``(impath, pid, camid, dsetid)``. This variable denotes the dataset ID and is useful when combining multiple datasets for training (as a dataset indicator). E.g., when combining ``market1501`` and ``cuhk03``, the former will be assigned ``dsetid=0`` while the latter will be assigned ``dsetid=1``. (2) Added ``RandomDatasetSampler``. Analogous to ``RandomDomainSampler``, ``RandomDatasetSampler`` samples a certain number of images (``batch_size // num_datasets``) from each of specified datasets (the amount is determined by ``num_datasets``).
- [Aug 2020] ``1.2.6``: Added ``RandomDomainSampler`` (it samples ``num_cams`` cameras each with ``batch_size // num_cams`` images to form a mini-batch).
- [Jun 2020] ``1.2.5``: (1) 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. (2) Added ``k_tfm`` as an option to image data loader, which allows data augmentation to be applied ``k_tfm`` times *independently* to an image. If ``k_tfm > 1``, ``imgs=data['img']`` returns a list with ``k_tfm`` image tensors.
- [Aug 2020] ``v1.3.3``: Fixed bug in ``visrank`` (caused by not unpacking ``dsetid``).
- [Aug 2020] ``v1.3.2``: Added ``_junk_pids`` to ``grid`` and ``prid``. This avoids using mislabeled gallery images for training when setting ``combineall=True``.
- [Aug 2020] ``v1.3.0``: (1) Added ``dsetid`` to the existing 3-tuple data source, resulting in ``(impath, pid, camid, dsetid)``. This variable denotes the dataset ID and is useful when combining multiple datasets for training (as a dataset indicator). E.g., when combining ``market1501`` and ``cuhk03``, the former will be assigned ``dsetid=0`` while the latter will be assigned ``dsetid=1``. (2) Added ``RandomDatasetSampler``. Analogous to ``RandomDomainSampler``, ``RandomDatasetSampler`` samples a certain number of images (``batch_size // num_datasets``) from each of specified datasets (the amount is determined by ``num_datasets``).
- [Aug 2020] ``v1.2.6``: Added ``RandomDomainSampler`` (it samples ``num_cams`` cameras each with ``batch_size // num_cams`` images to form a mini-batch).
- [Jun 2020] ``v1.2.5``: (1) 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. (2) Added ``k_tfm`` as an option to image data loader, which allows data augmentation to be applied ``k_tfm`` times *independently* to an image. If ``k_tfm > 1``, ``imgs=data['img']`` returns a list with ``k_tfm`` image tensors.
- [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.
- [May 2020] ``v1.2.1``: 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``.
- [Apr 2020] Upgraded to ``1.2.0``. The engine class has been made more model-agnostic to improve extensibility. See `Engine <torchreid/engine/engine.py>`_ and `ImageSoftmaxEngine <torchreid/engine/image/softmax.py>`_ for more details. Credit to `Dassl.pytorch <https://github.com/KaiyangZhou/Dassl.pytorch>`_.
- [Apr 2020] Upgraded to ``v1.2.0``. The engine class has been made more model-agnostic to improve extensibility. See `Engine <torchreid/engine/engine.py>`_ and `ImageSoftmaxEngine <torchreid/engine/image/softmax.py>`_ for more details. Credit to `Dassl.pytorch <https://github.com/KaiyangZhou/Dassl.pytorch>`_.
- [Dec 2019] Our `OSNet paper <https://arxiv.org/pdf/1905.00953v6.pdf>`_ has been updated, with additional experiments (in section B of the supplementary) showing some useful techniques for improving OSNet's performance in practice.
- [Nov 2019] ``ImageDataManager`` can load training data from target datasets by setting ``load_train_targets=True``, and the train-loader can be accessed with ``train_loader_t = datamanager.train_loader_t``. This feature is useful for domain adaptation research.