Torchreid: Deep learning person re-identification in PyTorch.
Basically a more stable version.
Added new dataset, models and tools.
Major updates:
argparse
are replaced with config.configs/
.use_cpu
is changed to use_gpu
.batch_size
is changed to batch_size_train
and batch_size_test
.Main update:
Bug fix: resize image to the target size in the training transformation function
Major updates:
compute_model_complexity()
.shufflenetv2
.Major updates:
rerank=True
in engine.run()
. It only works in the evaluation mode, i.e. test_only=True
.normalize_feature
to engine.run()
to allow the feature vectors to be normalized with L2 norm before calculating feature distance.Major changes:
combineall
https://github.com/KaiyangZhou/deep-person-reid/commit/bb6dc46e21e335789b9d891f7191c1da3a5d2e01