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
│ ├── bounding_box_test
│ ├── bounding_box_train
│ ├── query
│ ├── attribute
│ ├── duke_attribute.mat
Trained model are provided. You may download it from Google Drive or Baidu Drive (提取码:jpks). You may download it and move checkpoints
folder to your project's root directory.
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
19-08-23: Released trained models.
19-01-09: Fixed the error caused by an update of market and duke attribute dataset.