A baseline model ( pytorch implementation ) for person attribute recognition task, training and testing on Market1501-attribute and DukeMTMC-reID-attribute dataset.
You can get Market1501-attribute and DukeMTMC-reID-attribute annotations from here. Also you need to download Market-1501 and DukeMTMC-reID dataset.
Then, create a folder named 'attribute' under your dataset path, and put corresponding annotations into the folder.
For example,
~/dataset/DukeMTMC-reID/
~/dataset/DukeMTMC-reID/bounding_box_test/
~/dataset/DukeMTMC-reID/bounding_box_train/
~/dataset/DukeMTMC-reID/query/
~/dataset/DukeMTMC-reID/attribute/
~/dataset/DukeMTMC-reID/attribute/duke_attribute.mat
python3 train.py --data-path ~/dataset --dataset [market | duke] --model resnet50
python3 test.py --data-path ~/dataset --dataset [market | duke] --model resnet50
Market-1501 gallery:
average accuracy: 0.9024
DukeMTMC-reID gallery:
average accuracy: 0.8800
19-01-09: Fixed the error caused by an update of market and duke attribute dataset.