README.md

IoU-Enhanced-Attention

IoU-Enhanced Attention for End-to-End Task Specific Object Detection

Paper

IoU-Enhanced Attention for End-to-End Task Specific Object Detection

Models

Method	box AP	download
R50_100pro_3x	44.4	model
R50_300pro_3x	46.4	model
R101_100pro_3x	45.6	model
R101_300pro_3x	47.5	model

Models are available in Baidu Drive by code jysg.

Installation

The codebases are built on top of Detectron2 and SparseR-CNN.

Requirements

• Linux or macOS with Python ≥ 3.6
• PyTorch ≥ 1.5 and torchvision that matches the PyTorch installation. You can install them together at pytorch.org to make sure of this
• OpenCV is optional and needed by demo and visualization

Steps

1. Install and build libs

git clone https://github.com/bravezzzzzz/IoU-Enhanced-Attention.git
cd IoU-Enhanced-Attention
python setup.py build develop

2. Link coco dataset path to IoU-Enhanced-Attention/datasets/coco

mkdir -p datasets/coco
ln -s /path_to_coco_dataset/annotations datasets/coco/annotations
ln -s /path_to_coco_dataset/train2017 datasets/coco/train2017
ln -s /path_to_coco_dataset/val2017 datasets/coco/val2017

3. Train

python projects/SparseRCNN/train_net.py --num-gpus 8 \
    --config-file projects/SparseRCNN/configs/sparsercnn.res50.100pro.3x.yaml

4. Evaluate

python projects/SparseRCNN/train_net.py --num-gpus 8 \
    --config-file projects/SparseRCNN/configs/sparsercnn.res50.100pro.3x.yaml \
    --eval-only MODEL.WEIGHTS path/to/model.pth

5. Visualize

python demo/demo.py\
    --config-file projects/SparseRCNN/configs/sparsercnn.res50.100pro.3x.yaml \
    --input path/to/images --output path/to/save_images --confidence-threshold 0.4 \
    --opts MODEL.WEIGHTS path/to/model.pth

Citing

If you use this code for your research, please cite

@article{zhao2022iou,
  title={IoU-Enhanced Attention for End-to-End Task Specific Object Detection},
  author={Zhao, Jing and Wu, Shengjian and Sun, Li and Li, Qingli},
  journal={arXiv preprint arXiv:2209.10391},
  year={2022}
}