Torchreid: Deep learning person re-identification in PyTorch.
Removed prid450s.
This version should be stable.
Bug fix:
ImageDataset
or VideoDataset
rather than Dataset
.See the documentation https://kaiyangzhou.github.io/deep-person-reid/.
Major updates:
--label-smooth
should be called explicitly in order to add the label smoothing regularizer to the cross entropy loss.-s
and -t
, which refer to source datasets and target datasets, respectively. Both can take multiple strings delimited by space. For example, say you wanna train a model using Market1501+DukeMTMC-reID, just set -s market1501 dukemtmcreid
. If you wanna test on multiple datasets, you can do -t market1501 dukemtmcreid cuhk03 msmt17
.ImageDataManager
and VideoDataManager
(see data_manager.py). A datamanger is initialized by dm = ImageDataManager(use_gpu, **image_dataset_kwargs(args))
where image_dataset_kwargs()
is implemented in args.py
. Therefore, when new arguments are added to the data manager, you don't need to exhausively change everywhere in the code. What you need to update are (1) add new arguments in args.py
and (2) update the input arguments in data_manager.py
.--lambda-xent
and --lambda-htri
in xxx_xent_htri.py
, which can balance between cross entropy loss and hard mining triplet loss.dukemtmcreid
and dukemtmcvidreid
.--load-weights
(weights that don't match in size will be discarded, e.g. old classification layer).--vis-ranked-res
and reidtools.py
, allowing ranked images to be visualized.Note:
--use-lmdb
is postponed.
data_manager
is split into different scripts.--fixbase
option, allowing randomly initialized classifier layer to be trained while keeping base network frozen.To be done:
--lmdb
is under development.added cython-based evaluation.