Pytorch implementation of Transformer-based Dual Relation Graph for Multi-label Image Recognition. ICCV 2021
Python 3.6+
Pytorch 1.6
CUDA 10.1
Tesla V100 ×ばつ 2
- MS-COCO: the name of parameters in our original network is different from the public one, hence if you want to test the performance of TDRG on MS-COCO, please download the checkpoint into
checkpoint/COCO2014folder and replace the functionload_checkpointwithload_origin_checkpointintrainer.py.
CUDA_VISIBLE_DEVICES=0,1 python main.py --data COCO2014 --data_root_dir $DATA_PATH$ --save_dir $SAVE_PATH$ --i 448 --lr 0.03 -b 64
python main.py --data COCO2014 --data_root_dir $DATA_PATH$ --save_dir $SAVE_PATH$ --i 448 --lr 0.03 -b 64 -e --resume checkpoint/COCO2014/checkpoint_COCO.pth
- If you find this work is helpful, please cite our paper
@InProceedings{Zhao2021TDRG,
author = {Zhao, Jiawei and Yan, Ke and Zhao, Yifan and Guo, Xiaowei and Huang, Feiyue and Li, Jia},
title = {Transformer-Based Dual Relation Graph for Multi-Label Image Recognition},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2021},
pages = {163-172}
}