Skip to main content

MMKG Models

Project description

人-物交互关系检测使用说明

1. 算法描述

该算法用于人-物交互关系检测,检测图像内部细粒度人-物三元组列表。该算法基于PyTorch框架开发,输入文本与图像,输出人-物三元组关系列表及概率。

2. 依赖及安装

CUDA版本: 11.3 其他依赖库的安装命令如下:

conda install pytorch==1.9.0 torchvision==0.10.0 cudatoolkit=11.3

可使用如下命令下载安装算法包:

pip install -U mmkg-mm-hoi-detection

3. 使用示例及运行参数说明

from mmkg_mm_hoi_detection import MMHOIDetection
from PIL import Image
ckpt_path =  '***.pth'
model = MMHOIDetection(ckpt_path)
img_path = '***.jpg'
img = Image.open(img_path)
res,_ = model.inference(img,output_path='')

4. 论文

@article{liao2022gen,
  title={GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection},
  author={Liao, Yue and Zhang, Aixi and Lu, Miao and Wang, Yongliang and Li, Xiaobo and Liu, Si},
  journal={arXiv preprint arXiv:2203.13954},
  year={2022}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mmkg_mm_hoi_detection-0.1.3-py3-none-any.whl (1.5 MB view details)

Uploaded Python 3

File details

Details for the file mmkg_mm_hoi_detection-0.1.3-py3-none-any.whl.

File metadata

File hashes

Hashes for mmkg_mm_hoi_detection-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 994ef1ea393bac98a9d28697d5bf9c8a332b58ec3de14c928839f65ed7124126
MD5 d2de9047ebdddc8f33d5df947a2e58c4
BLAKE2b-256 fe20bd1edbd529c4ccf069ff91d1bef5eb066c2f39cef8dcaa4a8ffb4d515d34

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page